© 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. 151443
    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
    iangle
    -0.27
    ivol
    -0.26
     {:
    -0.26
     ].
    -0.25
    ith
    -0.25
    ãĢij↵↵
    -0.25
     ]↵↵
    -0.25
    鸨
    -0.25
    atab
    -0.24
    ihan
    -0.24
    POSITIVE LOGITS
    çĽĬ
    0.24
    æļij
    0.24
    rought
    0.24
    æľ¨èĢ³
    0.24
    æĭ¥æĮ¤
    0.24
    /pm
    0.23
    entlich
    0.23
    æ¯Ķè¾ĥ
    0.23
     spear
    0.23
    _ALLOW
    0.23
    Activations Density 0.295%

    No Known Activations

    This feature has no known activations.