© 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. 112972
    Prev
    Next
    INDEX
    Explanations

    Legal/official documents

    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
     ëķĮ문ìĿ´ëĭ¤
    -0.30
    izu
    -0.28
    touches
    -0.27
    ös
    -0.26
    è¿Ļç§įæĸ¹æ³ķ
    -0.26
     Tear
    -0.26
    geführt
    -0.25
    ово
    -0.25
    ãĤĪãģŃ
    -0.25
    ialog
    -0.24
    POSITIVE LOGITS
    ç»ĻæĤ¨
    0.27
     illum
    0.27
    为æĤ¨
    0.26
    è§ĨåIJ¬èĬĤ缮
    0.25
    gettext
    0.25
    丰ç¡ķ
    0.25
    çİĸ
    0.24
    æ´ĭ
    0.24
    ustin
    0.24
    illum
    0.23
    Activations Density 0.010%

    No Known Activations