© 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. 108614
    Prev
    Next
    INDEX
    Explanations

    hyphens or brackets

    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
     rounds
    -0.31
    ingu
    -0.29
    èĢģ乡
    -0.28
     mistaken
    -0.25
     nue
    -0.24
    propri
    -0.24
     victims
    -0.24
    å®ŀè´¨
    -0.24
    岿
    -0.23
    /maps
    -0.23
    POSITIVE LOGITS
    unded
    0.29
    oned
    0.27
    unj
    0.25
     geçir
    0.24
     Lit
    0.24
    zeit
    0.24
    odable
    0.24
    outh
    0.24
    毫
    0.24
    stringLiteral
    0.23
    Activations Density 0.117%

    No Known Activations