© 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. 12-TRANSCODER-HP
    7. 22975
    Prev
    Next
    INDEX
    Explanations

    arch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĽ´æ£ĭ
    -0.28
    åĨĻåŃĹ
    -0.26
    ä¸ºä½ł
    -0.26
    åIJ¸
    -0.25
    strup
    -0.25
    iola
    -0.24
     AK
    -0.24
     laz
    -0.24
     SPELL
    -0.24
    locale
    -0.23
    POSITIVE LOGITS
    yn
    0.29
     Modify
    0.26
    éĤ£æŶåĢĻ
    0.26
    é£Łçī©
    0.25
    YN
    0.25
    åįģä¸ĥæĿ¡
    0.25
     Nob
    0.24
    ency
    0.24
     noble
    0.24
    pecified
    0.24
    Activations Density 0.002%

    No Known Activations