© 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. 107652
    Prev
    Next
    INDEX
    Explanations

    Already done, previously existing

    np_max-act · gemini-2.0-flash
    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
    åģĩè£ħ
    -0.27
    个交æĺĵ
    -0.27
     åķĨåĵģ
    -0.25
    orst
    -0.25
    åķĨåĵģ
    -0.24
    ượ
    -0.24
     professionally
    -0.24
    pageNumber
    -0.23
    Commerce
    -0.23
    (targetEntity
    -0.23
    POSITIVE LOGITS
     apart
    0.32
     rep
    0.29
    奶油
    0.28
    Sparse
    0.27
    APE
    0.27
    èĦ±
    0.26
    éĽ¾
    0.26
    æĹ·
    0.26
    fp
    0.26
    uche
    0.26
    Activations Density 7.933%

    No Known Activations