© 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. 112818
    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
     Counts
    -0.24
    æĭ¾
    -0.24
    wel
    -0.24
    woord
    -0.23
     Picks
    -0.23
    DBObject
    -0.23
    ahr
    -0.23
    累积
    -0.23
    paque
    -0.23
    ständ
    -0.23
    POSITIVE LOGITS
    å°±ä¸ļ
    0.24
     resumed
    0.24
    /***/
    0.24
    æĨ©
    0.24
    //-
    0.24
    _then
    0.24
    Cong
    0.23
    Criterion
    0.23
    istent
    0.23
     tendencies
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.