© 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. 9272
    Prev
    Next
    INDEX
    Explanations

    virginia

    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
    zb
    -0.28
    fortune
    -0.26
    .places
    -0.26
    èĥ½åľ¨
    -0.26
    è¨Ĭ
    -0.25
    anje
    -0.25
    éĽ¢ãĤĮ
    -0.24
     characteristic
    -0.24
    кÑĤ
    -0.23
     hypert
    -0.23
    POSITIVE LOGITS
    HING
    0.27
     axial
    0.27
    LER
    0.26
     Sole
    0.26
    ä¼ĺåħĪ
    0.25
    æĹ¥
    0.24
     dome
    0.24
    банк
    0.24
    åĹĴ
    0.23
    å¢Ļå£ģ
    0.23
    Activations Density 0.003%

    No Known Activations