© 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. 31-TRANSCODER-HP
    7. 18159
    Prev
    Next
    INDEX
    Explanations

    articles or stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æģª
    -0.27
     Offices
    -0.27
    ORTH
    -0.26
    åĬŀåħ¬
    -0.26
    reste
    -0.26
    广åijĬæľįåĬ¡
    -0.25
    åĪĽ
    -0.25
     Populate
    -0.25
    çķĻè¨ĢæĿ¿
    -0.25
    åħ¬è®¤
    -0.24
    POSITIVE LOGITS
    éķ¿åº¦
    0.35
    åħĥ
    0.33
    metadata
    0.31
     introduced
    0.31
     metadata
    0.30
     released
    0.30
    åľ¨è¿ĻéĩĮ
    0.29
     fabricated
    0.29
     distributed
    0.28
     written
    0.28
    Activations Density 0.113%

    No Known Activations