© 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. 20-TRANSCODER-HP
    7. 107859
    Prev
    Next
    INDEX
    Explanations

    miscellaneous articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ·»
    -0.37
     íĺ¸
    -0.26
    ATEST
    -0.25
    碧
    -0.25
    {text
    -0.25
    åŃ©
    -0.24
    .Ac
    -0.24
    çĶ¨æĪ·æıIJä¾Ľ
    -0.24
    inent
    -0.24
    åŁİå¸Ĥåıijå±ķ
    -0.23
    POSITIVE LOGITS
    èŀį
    0.26
    aret
    0.26
    emic
    0.26
    aines
    0.26
     individual
    0.26
    rop
    0.25
    èĭ¥æĺ¯
    0.25
     Collabor
    0.25
    (/*
    0.24
    Æ°u
    0.24
    Activations Density 1.225%

    No Known Activations