© 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. 22-TRANSCODER-HP
    7. 111327
    Prev
    Next
    INDEX
    Explanations

    Problems, difficulties, negative consequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ksen
    -0.31
    æĪijä¼ļ
    -0.28
    Mui
    -0.26
    주ìĿĺ
    -0.26
    avatars
    -0.26
    大ä¼Ĺ
    -0.26
    æĪij们ä¼ļ
    -0.25
    à¸Ħà¸ĩ
    -0.24
     uncon
    -0.24
     yourselves
    -0.23
    POSITIVE LOGITS
    yr
    0.29
    LOS
    0.29
    FR
    0.25
    ertools
    0.24
     prés
    0.24
    AF
    0.24
    drv
    0.24
    åºŁ
    0.24
     presente
    0.23
     présent
    0.23
    Activations Density 0.036%

    No Known Activations