© 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. 32-TRANSCODER-HP
    7. 42289
    Prev
    Next
    INDEX
    Explanations

    Code and markup delimiters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĮħ
    -0.28
     trần
    -0.27
    à°¦
    -0.26
    vous
    -0.26
    odoxy
    -0.25
    lit
    -0.25
    è°Ĺ
    -0.25
     dumps
    -0.25
    .Constraint
    -0.24
    endcode
    -0.24
    POSITIVE LOGITS
    ((↵
    0.28
     Span
    0.26
    ä¸ŃåĽ½ç»ıæµİ
    0.25
    ik
    0.25
    å±ķæľĽ
    0.24
    åľ°ä¸Ĭ
    0.24
    大åıij
    0.24
    æ·±æ·±åľ°
    0.23
    åĬ¨åijĺ
    0.23
    Perfect
    0.23
    Activations Density 0.031%

    No Known Activations