© 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. 149481
    Prev
    Next
    INDEX
    Explanations

    Kh

    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
    Not in Any Lists

    No Comments

    Negative Logits
    -0.27
    estone
    -0.27
    ertools
    -0.27
     Hispan
    -0.25
    liner
    -0.25
    æĮº
    -0.24
    çĥ¬
    -0.24
     Neuroscience
    -0.24
    Reviewed
    -0.23
    ÑĤек
    -0.23
    POSITIVE LOGITS
    éĿ¢æĿ¿
    0.28
     summ
    0.27
    åĮĸçļĦ
    0.27
    è¨ĵ
    0.25
    åŃĹåı·
    0.25
    monthly
    0.24
    èģĶç½ij
    0.23
    aut
    0.23
     siti
    0.23
    èĢ¦
    0.23
    Activations Density 0.886%

    No Known Activations