© 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. 87095
    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
    leases
    -0.33
    èĥ¼
    -0.30
    ä¸Ģè¶Ł
    -0.27
    rão
    -0.26
    第ä¸ĢæĿ¡
    -0.25
    éĩľ
    -0.25
    pta
    -0.25
    ä¸ŃéĢĶ
    -0.25
    .Microsoft
    -0.25
    å¸IJåı·
    -0.25
    POSITIVE LOGITS
    0.28
    åª
    0.27
    æĺĵ
    0.27
    heet
    0.27
    uttle
    0.26
    è½½ä½ĵ
    0.26
    ç«ĭ
    0.26
    è¯į
    0.24
     Kar
    0.24
    ä½ĵ
    0.24
    Activations Density 0.032%

    No Known Activations

    This feature has no known activations.