© 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. 129240
    Prev
    Next
    INDEX
    Explanations

    from

    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
    Not in Any Lists

    No Comments

    Negative Logits
    _Framework
    -0.26
     skins
    -0.26
    rais
    -0.25
    -visible
    -0.25
    CHR
    -0.25
    Sit
    -0.24
     stat
    -0.24
     Morr
    -0.24
     situación
    -0.24
    æ¶Ī
    -0.24
    POSITIVE LOGITS
     tomorrow
    0.31
    azzi
    0.28
    ç¹ģçIJIJ
    0.28
    çIJIJ
    0.28
    åı¯èĥ½åŃĺåľ¨
    0.26
    æ¸ļ
    0.26
     fora
    0.25
    è¾¹
    0.25
    ç¹ģ
    0.25
    soles
    0.25
    Activations Density 0.005%

    No Known Activations