© 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. 9298
    Prev
    Next
    INDEX
    Explanations

    social

    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
    好åIJĹ
    -0.28
     quietly
    -0.27
    ÑģоÑĢ
    -0.26
    ÑģеÑĤ
    -0.25
    ë¥ĺ
    -0.25
    NEL
    -0.25
    é¼ł
    -0.25
     sch
    -0.24
    ORIZ
    -0.24
    lé
    -0.24
    POSITIVE LOGITS
    ppv
    0.28
    åĽ½å®¶éĺŁ
    0.27
    usted
    0.27
    zell
    0.27
    bindings
    0.27
     exem
    0.27
    åĭī
    0.26
    å¥łåŁº
    0.26
    ä¸ŃåĽ½æĶ¿åºľ
    0.26
    çĩ®
    0.26
    Activations Density 0.001%

    No Known Activations