© 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. 30-TRANSCODER-HP
    7. 96300
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.40
    åĵªéĩĮ
    -0.32
    åIJİèĢħ
    -0.31
     those
    -0.30
    大家
    -0.29
    åīįèĢħ
    -0.28
     this
    -0.26
    ä»ĸ人
    -0.25
    obby
    -0.25
     him
    -0.25
    POSITIVE LOGITS
    åľ¨åĮĹ京
    0.30
     Rican
    0.29
    åľ¨ç¾İåĽ½
    0.28
    ÑĢÑĥж
    0.28
    对åѦçĶŁ
    0.27
    ¬ģ
    0.27
    azar
    0.27
    åľ¨äº¬
    0.26
    åľ¨æ·±åľ³
    0.26
    .Modules
    0.25
    Activations Density 1.409%

    No Known Activations