© 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. 27-TRANSCODER-HP
    7. 8937
    Prev
    Next
    INDEX
    Explanations

    dialog box

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éģ¥æݧ
    -0.27
    ximity
    -0.27
    ·æĸ°
    -0.25
    éĿ¢å¯¹éĿ¢
    -0.25
     remot
    -0.25
    -desktop
    -0.25
    _present
    -0.24
    .centerY
    -0.23
    åĪ°åľº
    -0.23
    éĿ¢å¯¹
    -0.23
    POSITIVE LOGITS
    where
    0.34
     where
    0.31
    Where
    0.30
     Where
    0.28
    Exc
    0.27
    (where
    0.26
     FL
    0.26
    æĢ§çļĦ
    0.25
    show
    0.25
    .where
    0.25
    Activations Density 0.007%

    No Known Activations