© 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. 149476
    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
    Not in Any Lists

    No Comments

    Negative Logits
     flags
    -0.27
     speeches
    -0.27
     дÑĥÑħ
    -0.27
     elim
    -0.27
    å±ħ
    -0.26
     Flags
    -0.26
    flag
    -0.25
    heartbeat
    -0.25
     cellspacing
    -0.25
     teardown
    -0.25
    POSITIVE LOGITS
    尾巴
    0.26
    anca
    0.26
    лей
    0.26
    ]:č↵
    0.25
    åı®
    0.25
    åħ¨å¥Ĺ
    0.24
    è£ħå¤ĩ
    0.24
    éĻ¤å¤ĸ
    0.24
    onden
    0.24
    owania
    0.24
    Activations Density 2.060%

    No Known Activations

    This feature has no known activations.