© 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. 24412
    Prev
    Next
    INDEX
    Explanations

    Comparative words

    np_max-act · gemini-2.0-flash
    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
    æĥ³è±¡
    -0.53
    æ¯ĶæĪij
    -0.51
    æĥ³åĥı
    -0.40
    æ¯Ķ
    -0.40
     imagined
    -0.38
    ä¸įåĥı
    -0.37
    ä½łä»¥ä¸º
    -0.36
    -than
    -0.35
     Imagine
    -0.34
    ä½łæĥ³
    -0.33
    POSITIVE LOGITS
     hoje
    0.28
    efs
    0.27
    é½IJé²ģ
    0.26
     Rid
    0.25
    eon
    0.25
    É¡
    0.25
    ä½Ĩçİ°åľ¨
    0.25
    obile
    0.25
    ÑĢенд
    0.24
    -at
    0.24
    Activations Density 0.005%

    No Known Activations