© 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. 22422
    Prev
    Next
    INDEX
    Explanations

    finance and economics

    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
    èĤŁ
    -0.27
    ACING
    -0.26
    romo
    -0.26
     promin
    -0.26
    ormap
    -0.26
    _|
    -0.25
    بات
    -0.25
    é¨
    -0.25
     Earl
    -0.25
     pry
    -0.25
    POSITIVE LOGITS
    ("[%
    0.28
    ä¸įåı¯èĥ½
    0.26
     rubbed
    0.25
    usters
    0.25
     renew
    0.25
    -sum
    0.25
    ɾ
    0.25
    éģĵ
    0.25
     conf
    0.25
    æ·±åĮĸ
    0.24
    Activations Density 0.000%

    No Known Activations