© 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. 149299
    Prev
    Next
    INDEX
    Explanations

    code, software context

    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
     Used
    -0.27
     normally
    -0.27
     used
    -0.26
    ideshow
    -0.26
     corresponding
    -0.26
     ordinarily
    -0.25
     Chance
    -0.25
    Used
    -0.25
    ression
    -0.25
    -used
    -0.24
    POSITIVE LOGITS
    æĴĴ
    0.30
    éĩįå¿ĥ
    0.28
     lia
    0.28
    åĩĨ
    0.28
    lio
    0.26
    æľīä¸ĢçĤ¹
    0.25
    é«ĺä»·
    0.25
    ä½İä»·
    0.25
    обилÑĮ
    0.25
    æ´ģ
    0.24
    Activations Density 0.488%

    No Known Activations