© 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. 108633
    Prev
    Next
    INDEX
    Explanations

    bring

    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
     pena
    -0.25
    èĪĢ
    -0.25
    TokenType
    -0.25
     Kunden
    -0.24
    olf
    -0.24
    tf
    -0.24
    fdc
    -0.24
    ovenant
    -0.24
    .tokens
    -0.24
    uttle
    -0.23
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥
    0.28
    inged
    0.28
    bane
    0.28
    aths
    0.27
    quee
    0.26
    Insn
    0.25
    åľ¨å¤ĸ
    0.25
    iations
    0.25
    geries
    0.25
    DATES
    0.25
    Activations Density 0.907%

    No Known Activations