© 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. 20-TRANSCODER-HP
    7. 64027
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bapt
    -0.30
     beasts
    -0.28
    åijĬè¯ī她
    -0.27
     beast
    -0.27
    >*/↵
    -0.27
    æľīæľºç»ĵåIJĪ
    -0.26
    .getItemId
    -0.26
    bat
    -0.26
     Bapt
    -0.26
    burn
    -0.25
    POSITIVE LOGITS
    Domain
    0.29
    private
    0.26
    æľ¬
    0.26
     Domain
    0.26
    /domain
    0.26
    .Private
    0.25
    çĽij管
    0.25
    domain
    0.25
    /private
    0.25
    _domain
    0.25
    Activations Density 21.204%

    No Known Activations

    This feature has no known activations.