© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 86777
    Prev
    Next
    INDEX
    Explanations

    and

    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
    Negative Logits
    ä¸ĢåĪĻ
    -0.26
    ä¸ĢæĿ¡
    -0.26
    åĵį
    -0.26
    åįķ项
    -0.26
    缸åħ³äººåijĺ
    -0.25
    人æ°ijå¸ģ
    -0.25
    ais
    -0.25
    yst
    -0.25
    äºĴåĬ©
    -0.24
    俺
    -0.24
    POSITIVE LOGITS
    ,but
    0.25
    lename
    0.24
    datable
    0.24
    onga
    0.24
    lesc
    0.23
    ä¸įå¿į
    0.23
     leg
    0.23
    rips
    0.23
     tamil
    0.23
    len
    0.23
    Activations Density 0.004%

    No Known Activations