© 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. 110951
    Prev
    Next
    INDEX
    Explanations

    Lacking something

    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
    æĹłéľĢ
    -0.29
     WITHOUT
    -0.29
    å¦Ĥæŀľä¸į
    -0.28
    ä¸į失
    -0.28
    Without
    -0.28
    èĢĮä¸į
    -0.28
     Without
    -0.27
    without
    -0.26
    _without
    -0.26
    ä¸įéľĢè¦ģ
    -0.26
    POSITIVE LOGITS
    éĽİ
    0.26
    ç¹ģçIJIJ
    0.25
    åıįåĵį
    0.25
     getLocation
    0.25
    _DATABASE
    0.24
    æĮīè§Ħå®ļ
    0.24
    æĮ¨
    0.24
     painstaking
    0.23
    óst
    0.23
    æĭ¼éŁ³
    0.23
    Activations Density 0.021%

    No Known Activations