© 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. 8815
    Prev
    Next
    INDEX
    Explanations

    ph

    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
     Petro
    -0.30
     Volk
    -0.27
    uib
    -0.25
    _strength
    -0.25
    _STRUCTURE
    -0.24
     fib
    -0.24
     fiss
    -0.24
    ieran
    -0.24
     PROT
    -0.24
    oteca
    -0.23
    POSITIVE LOGITS
    äºī
    0.26
     malign
    0.25
     District
    0.25
     mente
    0.25
    áĢĨ
    0.25
    åı¦å¤ĸ
    0.25
    mine
    0.24
    District
    0.24
    æľīè¿ĩ
    0.24
    æľĢåIJĪéĢĤ
    0.24
    Activations Density 0.003%

    No Known Activations