© 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. 25-TRANSCODER-HP
    7. 108314
    Prev
    Next
    INDEX
    Explanations

    Detecting unusual text fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èµ·æĿ¥äºĨ
    -0.27
    ufs
    -0.26
    .Pointer
    -0.26
    ä¿İ
    -0.25
     zf
    -0.25
    edin
    -0.25
    sequelize
    -0.25
    compet
    -0.24
    é£İåIJ¹
    -0.24
    encil
    -0.24
    POSITIVE LOGITS
    cro
    0.30
    ä¸ºä½ł
    0.27
    çŃĭ
    0.26
    erging
    0.26
    LY
    0.26
    cert
    0.26
     Kont
    0.25
    ики
    0.25
     cro
    0.25
     Far
    0.25
    Activations Density 1.045%

    No Known Activations