© 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. 62988
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    足
    -0.30
    èݲ
    -0.26
    é¼ĵèĪŀ
    -0.25
    Gap
    -0.24
    gap
    -0.24
    bay
    -0.23
     Ole
    -0.23
     Lies
    -0.23
    ä¸ĭåĪĹ
    -0.23
    æĿİåħĪçĶŁ
    -0.23
    POSITIVE LOGITS
    inati
    0.28
    á»ĵn
    0.26
    为æ°ij
    0.26
    keiten
    0.25
    ä¿İ
    0.24
    ä¸Ģä½ĵ
    0.24
    itioner
    0.24
    éļ¾éģĵ
    0.24
    elves
    0.23
    æĪĹ
    0.23
    Activations Density 2.132%

    No Known Activations