© 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. 19356
    Prev
    Next
    INDEX
    Explanations

    Non-English / abbreviations

    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
     neighborhood
    -0.28
     Neighborhood
    -0.27
     neighbourhood
    -0.26
    íĭĢ
    -0.25
    fte
    -0.25
    æµģåŁŁ
    -0.25
     Cellular
    -0.25
    åľ°æĸ¹
    -0.24
    åį±æľº
    -0.24
     repetition
    -0.24
    POSITIVE LOGITS
    åºĸ
    0.31
    çĽ¸å¯¹è¾ĥ
    0.28
    oref
    0.26
    ivr
    0.26
    ibase
    0.25
    ç½ij讯
    0.24
    olls
    0.24
     intensive
    0.24
    oked
    0.24
     expires
    0.24
    Activations Density 0.968%

    No Known Activations