© 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. 108310
    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
    orne
    -0.27
     bald
    -0.26
    chied
    -0.26
    rone
    -0.25
     torn
    -0.25
     assist
    -0.25
     associative
    -0.25
    åijĬè¯ī她
    -0.24
     neutral
    -0.24
     empt
    -0.24
    POSITIVE LOGITS
    Ger
    0.29
     Ger
    0.27
    ä¸ĭæ²ī
    0.26
    å¿Ĵ
    0.26
     Yad
    0.26
    append
    0.25
    ire
    0.25
    ç»Ĩ
    0.24
    ä¸įè¿ĩ
    0.24
    YO
    0.24
    Activations Density 0.911%

    No Known Activations

    This feature has no known activations.