© 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. 130687
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    çĬŁ
    -0.27
    çħ
    -0.26
    invert
    -0.25
    ä½ĵä¼ļåĪ°
    -0.25
    createClass
    -0.24
     Constantin
    -0.24
    ines
    -0.24
    orea
    -0.23
    ä¼ļä¸įä¼ļ
    -0.23
    èĻ¾
    -0.23
    POSITIVE LOGITS
    (||
    0.29
    assic
    0.28
     cents
    0.27
    彩èĻ¹
    0.25
    館
    0.25
    CLS
    0.25
    é¦ĸ
    0.24
    磺
    0.23
    ç¾İåĽ½æĢ»ç»Ł
    0.23
    飧
    0.23
    Activations Density 0.027%

    No Known Activations