© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107108
    Prev
    Next
    INDEX
    Explanations

    Website navigation and code

    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
    Negative Logits
    ozo
    -0.28
    磮
    -0.26
    æ²¥
    -0.26
    ìłķë³´
    -0.26
    åĩºãģĻ
    -0.25
    çħ§
    -0.25
    ![↵
    -0.25
    .Par
    -0.24
    :path
    -0.24
    iative
    -0.24
    POSITIVE LOGITS
    istem
    0.30
    oui
    0.26
    Injected
    0.26
    laden
    0.26
     quot
    0.26
    è¿Ľè¡ĮäºĨ
    0.25
    etter
    0.25
    irection
    0.24
    Age
    0.24
    isted
    0.24
    Activations Density 0.069%

    No Known Activations