© 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. 86822
    Prev
    Next
    INDEX
    Explanations

    0

    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
    aniem
    -0.28
    å¨ĺ家
    -0.27
    implements
    -0.25
     Lodge
    -0.25
    ENCE
    -0.25
    .*)
    -0.24
     accelerated
    -0.24
    (auth
    -0.24
    ))^
    -0.24
     accelerating
    -0.24
    POSITIVE LOGITS
    æŃ¥è¡Į
    0.31
    éĢ¢
    0.26
    æĽ²æĬĺ
    0.25
    лев
    0.25
    临æŶ
    0.24
    rets
    0.24
    æĶ¶éĽĨ
    0.24
    形象
    0.24
    æľīä¸ĢçĤ¹
    0.23
    ysis
    0.23
    Activations Density 0.093%

    No Known Activations