© 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. 27-TRANSCODER-HP
    7. 56732
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )[:
    -0.28
     prefixed
    -0.27
    娶
    -0.27
    aska
    -0.26
    èĩªæĿ¥
    -0.26
    .rabbit
    -0.25
    (bundle
    -0.25
    è¶Ĭ好
    -0.24
     rests
    -0.24
     (:
    -0.24
    POSITIVE LOGITS
    éĢĿ
    0.27
    å¸Ī
    0.26
     onsite
    0.26
    åĶĩ
    0.25
     practitioner
    0.25
    ocaust
    0.25
    æĴŀ
    0.25
    _PT
    0.25
    éĢ¼
    0.25
    FU
    0.25
    Activations Density 0.008%

    No Known Activations