© 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. 151269
    Prev
    Next
    INDEX
    Explanations

    world

    np_max-act-logits · gemini-2.0-flash
    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
    anja
    -0.34
    ç©Ĩ
    -0.27
    paramref
    -0.26
    ÐĦ
    -0.24
    ials
    -0.24
    tee
    -0.24
    ä¼´éļıçĿĢ
    -0.24
    ë³´
    -0.23
    纯æ´ģ
    -0.23
    æIJŃéħį
    -0.23
    POSITIVE LOGITS
     dominated
    0.29
    masters
    0.26
    èĩªæĿ¥
    0.25
     fix
    0.25
    以为
    0.25
     billed
    0.25
     known
    0.24
     widely
    0.24
     burst
    0.24
     resistant
    0.24
    Activations Density 0.905%

    No Known Activations