© 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. 24-TRANSCODER-HP
    7. 151371
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    lat
    -0.30
    踬
    -0.29
    åł°
    -0.26
    ÑįÑĤаж
    -0.26
    çĻ½é©¬
    -0.25
    гÑĢам
    -0.25
    æľĢæĸ°çļĦ
    -0.25
    DET
    -0.25
    det
    -0.24
    龸çİĭ
    -0.24
    POSITIVE LOGITS
    åĪĴ
    0.28
     threshold
    0.27
    ä¼Ĭ
    0.27
    èģ½
    0.27
    strate
    0.27
     pair
    0.26
     feedback
    0.26
    feedback
    0.25
    .feedback
    0.25
    æķĻèĤ²åŁ¹è®Ń
    0.25
    Activations Density 0.080%

    No Known Activations

    This feature has no known activations.