© 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. 108008
    Prev
    Next
    INDEX
    Explanations

    Technical documentation/code snippets

    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
    uela
    -0.27
     orc
    -0.27
     cá»Ļng
    -0.27
    CEED
    -0.27
    fdb
    -0.26
    æī¿æĭħ责任
    -0.26
    bee
    -0.24
    bsub
    -0.24
    opus
    -0.24
    Deal
    -0.24
    POSITIVE LOGITS
     Li
    0.27
    SourceType
    0.27
     facts
    0.25
     source
    0.25
    ographics
    0.24
    )?.
    0.24
    æ¡Ī
    0.24
     gravity
    0.24
     options
    0.24
     concepts
    0.24
    Activations Density 1.029%

    No Known Activations