© 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. 131095
    Prev
    Next
    INDEX
    Explanations

    Comparisons and analogies

    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
    olars
    -0.27
     feeds
    -0.25
    ç¡®
    -0.25
    coordinates
    -0.24
    åĿIJæłĩ
    -0.24
    ISE
    -0.24
    feeds
    -0.23
    olar
    -0.23
    oid
    -0.23
    .baidu
    -0.23
    POSITIVE LOGITS
    æĩĤäºĭ
    0.28
    nze
    0.25
     Thomson
    0.25
    abei
    0.24
    å°±çŁ¥éģĵ
    0.24
    WithValue
    0.24
    rawn
    0.24
    itness
    0.24
    urgeon
    0.24
    ä½ķæŶ
    0.23
    Activations Density 0.018%

    No Known Activations