© 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. 113047
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    è¼ī
    -0.30
    åķĨæĬ¥
    -0.29
     exc
    -0.28
    éĢļè¡Įè¯ģ
    -0.27
    Carrier
    -0.27
    elib
    -0.26
    év
    -0.25
    bidden
    -0.24
    æĹłè§Ĩ
    -0.24
     ContentType
    -0.24
    POSITIVE LOGITS
    /MIT
    0.26
    itori
    0.26
    å¾Ĺ天
    0.25
     Desk
    0.25
    çĶ¨äºĨ
    0.25
    formData
    0.24
    oug
    0.24
    è¿ĩäºĨ
    0.24
    å¾Ĺ
    0.24
    mentor
    0.23
    Activations Density 0.014%

    No Known Activations