© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24625
    Prev
    Next
    INDEX
    Explanations

    Contractions using "not"

    np_max-act · gemini-2.0-flash

    English negative contractions using "n't," often in auxiliary or modal verb constructions.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ļ座
    -0.27
    atus
    -0.27
    æĪ¿åŃIJ
    -0.27
    åѦåĪ°
    -0.26
    çľĭçĤ¹
    -0.25
    ignon
    -0.25
    åĩºèº«
    -0.25
    ATUS
    -0.25
    achable
    -0.24
    ä¸įå®Į
    -0.24
    POSITIVE LOGITS
    ä¸ĢéĿ¢
    0.27
     raz
    0.26
    elan
    0.26
    æ¯ĶæĭŁ
    0.26
    .Mapper
    0.25
    éĬ®
    0.25
    isque
    0.25
     Olympia
    0.25
     trop
    0.24
    okers
    0.24
    Activations Density 0.015%

    No Known Activations