© 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. 35-TRANSCODER-HP
    7. 39457
    Prev
    Next
    INDEX
    Explanations

    Places/regions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UM
    -0.27
    åĮĹæĸ¹
    -0.26
    ĭè¯ķ
    -0.26
    åįĹæĸ¹
    -0.26
    ç¢
    -0.25
    _bug
    -0.25
    igua
    -0.25
    ï¼´
    -0.25
    Northern
    -0.24
    åįĹéĥ¨
    -0.24
    POSITIVE LOGITS
     Americans
    0.33
     Australians
    0.32
     foreigners
    0.31
    ä¸ŃåĽ½äºº
    0.30
     Architects
    0.30
     Attend
    0.30
    ç¾İåĽ½äºº
    0.29
     attendees
    0.29
     Arbit
    0.27
     Canadians
    0.27
    Activations Density 8.120%

    No Known Activations