© 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. 128922
    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
    Negative Logits
    /MIT
    -0.29
    æį¢äºĨ
    -0.28
     crack
    -0.27
    é¾ĭ
    -0.27
     MIT
    -0.26
     enumerable
    -0.26
    æ³ķåĪ¶
    -0.26
     hooked
    -0.26
     cr
    -0.26
     tip
    -0.25
    POSITIVE LOGITS
    ä¸Ģæĸ¹
    0.28
    holders
    0.27
    standing
    0.27
    irected
    0.26
     Repos
    0.25
    Below
    0.25
    驳
    0.25
    ÑħоÑĤ
    0.24
    utton
    0.24
    ottie
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.