© 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. 24-TRANSCODER-HP
    7. 149577
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guar
    -0.30
    Neal
    -0.25
     NIL
    -0.24
    æĴ¸
    -0.24
    aise
    -0.24
    uali
    -0.24
    æįĨ
    -0.24
    åģļèµ·
    -0.24
     Nigel
    -0.24
    aille
    -0.23
    POSITIVE LOGITS
    ä½Ī
    0.28
     endforeach
    0.27
    ساب
    0.26
    ä»Ĺ
    0.25
    ston
    0.24
     Asians
    0.24
    çĿ¥
    0.24
    åĪ
    0.24
    èĸ®
    0.23
    çĪ¸çĪ¸å¦Īå¦Ī
    0.23
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.