© 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. 111239
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    å°±ä¸įèĥ½
    -0.29
    å°±æľīäºĨ
    -0.27
    æĹ¢æľī
    -0.27
     afford
    -0.26
    Seconds
    -0.25
    ancell
    -0.25
    odb
    -0.25
    å°±æĬĬ
    -0.25
    å¾Ĥ
    -0.25
    æľºåħ³
    -0.24
    POSITIVE LOGITS
    __('
    0.31
     ${(
    0.29
    printer
    0.29
    室
    0.28
    ï¼Ľ
    0.28
    æĴij
    0.27
     spar
    0.26
    __("
    0.26
    WINDOW
    0.25
    åľ¨æѤ
    0.25
    Activations Density 0.005%

    No Known Activations