© 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. 113033
    Prev
    Next
    INDEX
    Explanations

    Subject

    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
    ç©¿è¶Ĭ
    -0.25
    第ä¸ĢåIJį
    -0.25
    æ£ī
    -0.24
    ·¨
    -0.24
    .await
    -0.24
     Alexand
    -0.24
    cos
    -0.23
    åIJĪèµĦ
    -0.23
    æĪIJ为ä¸ĢåIJį
    -0.23
    âĹ»
    -0.23
    POSITIVE LOGITS
    errer
    0.28
    Overrides
    0.27
    ambi
    0.25
    pect
    0.25
     peaked
    0.25
     Geh
    0.24
    legates
    0.24
     âĸĪâĸĪ
    0.24
    (pm
    0.24
    ested
    0.24
    Activations Density 0.033%

    No Known Activations