© 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. 108463
    Prev
    Next
    INDEX
    Explanations

    and

    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
    atories
    -0.27
    é¢ļ
    -0.27
    æł¼
    -0.27
    onus
    -0.26
    è¾ķ
    -0.26
    uated
    -0.25
    ĽĦ
    -0.25
    tools
    -0.25
    两æīĭ
    -0.25
    åĬ¡
    -0.24
    POSITIVE LOGITS
    pson
    0.31
    apters
    0.27
     exhibit
    0.26
     artisan
    0.26
     fib
    0.26
    icer
    0.25
    zenia
    0.25
    esign
    0.25
    ion
    0.25
    ision
    0.24
    Activations Density 0.935%

    No Known Activations