© 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. 87112
    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
    -tools
    -0.26
     PHI
    -0.25
    GB
    -0.25
    ç´§å¯Ĩ
    -0.24
    -pills
    -0.24
    itored
    -0.24
    æĩ·
    -0.23
    ftime
    -0.23
    严å¯Ĩ
    -0.23
    istory
    -0.23
    POSITIVE LOGITS
    cad
    0.29
    /rem
    0.27
     fell
    0.27
    ä¼łåĩº
    0.24
    scenes
    0.24
    åı°
    0.24
     Zu
    0.24
     cad
    0.24
    éĺ¶æ®µæĢ§
    0.24
    æĮĤçīĮ
    0.23
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.