© 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. 22660
    Prev
    Next
    INDEX
    Explanations

    Action verbs

    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
    èĨı
    -0.26
    adratic
    -0.26
     lick
    -0.25
    éĿ¥
    -0.25
     separate
    -0.24
    vestment
    -0.24
     bed
    -0.24
     Oracle
    -0.23
    å¿ĥ
    -0.23
    çݦ
    -0.23
    POSITIVE LOGITS
    arma
    0.28
    NESS
    0.26
    pile
    0.26
    BD
    0.25
     ham
    0.25
    ë¡Ŀ
    0.24
     indirect
    0.24
     Strange
    0.24
    #undef
    0.23
    /operators
    0.23
    Activations Density 0.001%

    No Known Activations