© 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. 31-TRANSCODER-HP
    7. 19049
    Prev
    Next
    INDEX
    Explanations

    .example

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oring
    -0.27
    ег
    -0.26
    erged
    -0.25
     dyst
    -0.24
     bac
    -0.24
    åĹĿ
    -0.24
     traveller
    -0.23
    alic
    -0.23
     Braz
    -0.23
     brushing
    -0.23
    POSITIVE LOGITS
     functional
    0.29
    }@
    0.28
    rooms
    0.26
    å¤ļä¸ĩ
    0.26
     Functional
    0.25
    åįģä¸ĩ
    0.25
    ç¨
    0.24
    .toObject
    0.24
    æĹ¥æĬ¥éģĵ
    0.24
    -ves
    0.24
    Activations Density 1.025%

    No Known Activations