© 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. 107994
    Prev
    Next
    INDEX
    Explanations

    bass

    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
    ineTransform
    -0.29
    rames
    -0.28
    ksz
    -0.28
     Dund
    -0.26
    å·¥ç¨ĭæĬĢæľ¯
    -0.26
    halb
    -0.25
    REW
    -0.25
     yours
    -0.25
     Eylül
    -0.25
     normals
    -0.24
    POSITIVE LOGITS
    frequency
    0.28
    æ¸ĹéĢı
    0.28
     inherent
    0.26
    pur
    0.26
     Nur
    0.25
     grep
    0.25
    weights
    0.25
     charter
    0.25
    æĿ¿åĿĹ
    0.25
     Sponsor
    0.24
    Activations Density 0.088%

    No Known Activations