© 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. 130924
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ãĤ»ãĥ«
    -0.27
    èĵ¬
    -0.26
    ä¸ĢæĹı
    -0.25
    æ³Ħæ¼ı
    -0.25
     leap
    -0.24
    lemn
    -0.24
    篷
    -0.24
    ÐŁÐµÑĤеÑĢбÑĥÑĢг
    -0.23
    lesh
    -0.23
    /stretch
    -0.23
    POSITIVE LOGITS
    转
    0.29
    TTY
    0.29
    akter
    0.28
    ixa
    0.28
    äºĨ
    0.27
    avra
    0.25
    spinner
    0.25
    iku
    0.25
    æĪĸå¤ļ
    0.25
    opt
    0.25
    Activations Density 0.026%

    No Known Activations

    This feature has no known activations.