© 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. 108355
    Prev
    Next
    INDEX
    Explanations

    when

    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
     cent
    -0.30
    arta
    -0.30
    cket
    -0.27
     scalar
    -0.25
    丢失
    -0.25
    mt
    -0.25
    è¡°
    -0.25
    ctal
    -0.25
     Slut
    -0.25
    @qq
    -0.25
    POSITIVE LOGITS
     immedi
    0.29
    å¤§èµĽ
    0.27
    ace
    0.27
    tdown
    0.26
    ãĢĮ
    0.26
    ç«ŀä»·
    0.26
    å½ĵä¸ĭ
    0.26
    é¢Ħæµĭ
    0.26
    FER
    0.25
    té
    0.25
    Activations Density 0.914%

    No Known Activations