© 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. 86828
    Prev
    Next
    INDEX
    Explanations

    Opinions and suggestions

    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
    BERS
    -0.26
    ULER
    -0.26
    åıįèĢĮ
    -0.24
    ãĤ¹ãĤŃ
    -0.24
    atics
    -0.24
    æĪIJ为äºĨ
    -0.24
    Ø¢ÙĨ
    -0.24
    ----</
    -0.24
    欻
    -0.24
    culus
    -0.24
    POSITIVE LOGITS
    æľ¬åĽ½
    0.27
    èĩªå·±åĸľæ¬¢
    0.27
    alc
    0.25
    çĶµåŃIJ
    0.25
     decorated
    0.24
     adjustment
    0.24
     hab
    0.24
    ä¸ĸ代
    0.24
    ousse
    0.23
    æ¡Į
    0.23
    Activations Density 0.014%

    No Known Activations