© 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. 86753
    Prev
    Next
    INDEX
    Explanations

    connectors

    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»ĸå·²ç»ı
    -0.26
    ä¸Ģç¯ĩæĸĩç«ł
    -0.25
    bright
    -0.25
    ä»ĸè¿ĺ
    -0.23
    ä¸į失
    -0.23
    ä½Ĩä»ĸ
    -0.23
    estroy
    -0.23
    Fcn
    -0.23
    stamp
    -0.23
    blems
    -0.23
    POSITIVE LOGITS
    è°ģ
    0.28
    PAR
    0.28
    lew
    0.27
     saddle
    0.26
    ç½®
    0.26
    éĢļè¿ĩ
    0.25
     M
    0.25
    å§ĭäºİ
    0.24
    çĶ¨æīĭ
    0.24
     <>
    0.24
    Activations Density 0.005%

    No Known Activations