© 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. 149301
    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
    é£İéĻ©
    -0.27
    åĢ¼å¾Ĺåħ³æ³¨
    -0.26
    ä»·
    -0.26
    æĹłå¥Ī
    -0.24
    èijĹ
    -0.24
    éĤ»
    -0.24
    ressed
    -0.24
     exact
    -0.24
    åĥ¹
    -0.24
    éķĬ
    -0.24
    POSITIVE LOGITS
     handlers
    0.29
     Handlers
    0.29
     accommodation
    0.28
    -handler
    0.27
     ASA
    0.25
    Handlers
    0.25
     mediums
    0.25
    eward
    0.25
    handlers
    0.24
    warts
    0.24
    Activations Density 0.505%

    No Known Activations

    This feature has no known activations.