© 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. 57469
    Prev
    Next
    INDEX
    Explanations

    names in legal text

    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
     tender
    -0.31
    аÑĤÑĥÑĢ
    -0.30
     Tender
    -0.30
     bored
    -0.28
    ngen
    -0.27
    害ç¾ŀ
    -0.26
    YPD
    -0.26
    è¢Ĵ
    -0.25
    emade
    -0.25
    ĮĢ
    -0.25
    POSITIVE LOGITS
    REFERENCES
    0.27
    gest
    0.27
    /LICENSE
    0.26
    _Rel
    0.26
     Glo
    0.26
    ä¸Ńåħ³
    0.25
    bris
    0.25
    uish
    0.24
    ôn
    0.24
    ç¾¤å²Ľ
    0.24
    Activations Density 0.107%

    No Known Activations