© 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. 129259
    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
    åįĬ个
    -0.32
    aina
    -0.27
    ä¸Ģç¬Ķ
    -0.25
    äºĨä»ĸçļĦ
    -0.24
     receptions
    -0.24
    äºĮåŃĹ
    -0.24
    WR
    -0.23
    æ°Ļ
    -0.23
    .EventType
    -0.23
    rets
    -0.23
    POSITIVE LOGITS
    快讯
    0.28
    ige
    0.27
    >tag
    0.27
    æŁŀ
    0.26
    Donate
    0.25
     Ey
    0.24
    .fm
    0.24
    oth
    0.24
    |R
    0.24
     Gifts
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.