© 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. 12-TRANSCODER-HP
    7. 23274
    Prev
    Next
    INDEX
    Explanations

    areas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eous
    -0.30
    venida
    -0.28
     spelled
    -0.26
    åij¢
    -0.26
    venue
    -0.25
    ÑĩнаÑı
    -0.25
    æľ¨
    -0.24
    人åĿĩ
    -0.24
    æı½
    -0.24
    olith
    -0.24
    POSITIVE LOGITS
    rep
    0.34
    Rep
    0.30
    kits
    0.29
    (rep
    0.28
    imp
    0.27
     rep
    0.27
    .rep
    0.26
    sip
    0.26
    æŶæĬ¥
    0.26
    ä¸įåıĺ
    0.26
    Activations Density 0.000%

    No Known Activations