© 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. 97302
    Prev
    Next
    INDEX
    Explanations

    Comparisons

    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
    æ¯Ķ
    -0.38
    ustin
    -0.34
    -vs
    -0.32
     outnumber
    -0.31
    è¦ģæ¯Ķ
    -0.31
     vs
    -0.30
    æĪĺèĥľ
    -0.29
    å¯ĦãģĽ
    -0.28
    缸æ¯Ķäºİ
    -0.28
    è¶ħè¶Ĭ
    -0.28
    POSITIVE LOGITS
     parks
    0.26
     Neville
    0.25
     created
    0.25
    å¹²
    0.24
    好çļĦ
    0.24
    Increment
    0.24
    ä»ĵ
    0.24
     forecasts
    0.23
    .setValue
    0.23
    壹
    0.23
    Activations Density 0.002%

    No Known Activations