© 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. 107497
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    (KP
    -0.26
    æİ©
    -0.25
     exports
    -0.25
    perimental
    -0.25
    +p
    -0.25
    isel
    -0.24
     lay
    -0.24
    ers
    -0.24
     GK
    -0.24
    rough
    -0.24
    POSITIVE LOGITS
    é£ĵ
    0.29
    idue
    0.28
    è¿Ļ让
    0.28
     istediÄŁi
    0.26
    ĥģ
    0.26
    æµģæĦŁ
    0.26
    å¿ĥ仪
    0.26
    è¶ĬæĿ¥è¶Ĭ大
    0.25
    heimer
    0.25
    声称
    0.25
    Activations Density 0.268%

    No Known Activations

    This feature has no known activations.