© 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. 22-TRANSCODER-HP
    7. 111622
    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_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½ĵéªĮ
    -0.30
    erah
    -0.29
    dictions
    -0.27
    hen
    -0.25
     expressions
    -0.25
    ifers
    -0.25
    ajo
    -0.24
    برÙĬ
    -0.23
    èĩªåįij
    -0.23
    éĤº
    -0.23
    POSITIVE LOGITS
    Mean
    0.27
    æĺ¯æĪij们
    0.27
    æĿ¡
    0.25
    Õŀ
    0.25
    è®®äºĭ
    0.25
    .oracle
    0.25
    :=
    0.25
    X
    0.25
    -
    0.24
    ä¸Ģç«Ļå¼ı
    0.24
    Activations Density 0.012%

    No Known Activations