© 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. 130541
    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
    esta
    -0.25
     feat
    -0.25
    ä½łèĩªå·±
    -0.25
    ringe
    -0.25
    MS
    -0.25
    MING
    -0.25
    符
    -0.25
    宿
    -0.24
    strand
    -0.24
    (sf
    -0.24
    POSITIVE LOGITS
     resulting
    0.27
    ä¸įå¿ĺ
    0.24
    üm
    0.24
    åĴĮæĬĢæľ¯
    0.24
    并åIJij
    0.24
    ApiController
    0.24
     VER
    0.23
     dum
    0.23
    å½¼
    0.23
     unrecognized
    0.23
    Activations Density 0.008%

    No Known Activations