© 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. 112793
    Prev
    Next
    INDEX
    Explanations

    Code and instructions

    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
    æľªæĿ¥
    -0.31
    ä¸ĭä¸Ģ
    -0.30
    å°ĨæĿ¥
    -0.28
    æľīå¿ħè¦ģ
    -0.28
     próximo
    -0.28
    æĢ¥éľĢ
    -0.27
    ä¸ĢæŃ¥
    -0.27
    porto
    -0.26
    ä¸ĭä¸ĢæŃ¥
    -0.26
    æ´¥
    -0.26
    POSITIVE LOGITS
     invert
    0.29
    修为
    0.27
    invert
    0.27
     Surround
    0.27
     inverted
    0.26
    éĶĨ
    0.26
    æIJ¦
    0.26
    ]._
    0.26
    _("
    0.24
     reversed
    0.24
    Activations Density 0.002%

    No Known Activations