© 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. 35-TRANSCODER-HP
    7. 40204
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fi
    -0.40
    ï½Ĩ
    -0.36
    fä
    -0.36
     fi
    -0.34
    fü
    -0.33
    fa
    -0.33
    f
    -0.32
    fan
    -0.32
    fy
    -0.32
    fo
    -0.31
    POSITIVE LOGITS
    arts
    0.39
    isters
    0.39
     Nes
    0.38
    us
    0.37
    asts
    0.36
    unts
    0.36
    untas
    0.36
     us
    0.35
    isos
    0.35
    els
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.