© 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. 98651
    Prev
    Next
    INDEX
    Explanations

    prices

    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
    èĩªåıij
    -0.25
    anyl
    -0.25
    entar
    -0.25
    ademic
    -0.24
    .defaultProps
    -0.24
    .AttributeSet
    -0.24
    æ´¾åĩºæīĢ
    -0.24
    çľ¼ç¥ŀ
    -0.23
    .prefix
    -0.23
    pent
    -0.23
    POSITIVE LOGITS
    é£
    0.25
    们çļĦ
    0.25
     gast
    0.25
    ä¼ļåıijçĶŁ
    0.25
    ially
    0.25
    åį±æľº
    0.24
    åıijçĶŁäºĨ
    0.24
    ä¸įå¿į
    0.24
    å»Ĭ
    0.24
    ì¦Ŀ
    0.23
    Activations Density 0.004%

    No Known Activations