© 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. 27-TRANSCODER-HP
    7. 7664
    Prev
    Next
    INDEX
    Explanations

    computational topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç»´
    -0.32
    fac
    -0.30
     fac
    -0.30
    ç¶Ń
    -0.27
    ailable
    -0.26
     members
    -0.26
    _fac
    -0.26
    airs
    -0.26
     halves
    -0.25
    大人
    -0.25
    POSITIVE LOGITS
    rising
    0.32
    èĨ¨èĥĢ
    0.30
    jab
    0.29
    ization
    0.28
    squ
    0.28
    èĨı
    0.27
     cropping
    0.25
     ``
    0.25
     nale
    0.25
     getApp
    0.25
    Activations Density 0.001%

    No Known Activations