© 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. 151072
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     filesize
    -0.26
     UPC
    -0.25
    æĹłéĻIJ
    -0.24
     bib
    -0.24
    aviors
    -0.24
    ç´łè´¨
    -0.24
    æ±
    -0.24
     nextState
    -0.24
    tat
    -0.23
     entend
    -0.23
    POSITIVE LOGITS
    ç»Ħ
    0.29
    ya
    0.29
    æīĽ
    0.28
     sil
    0.26
    sterol
    0.26
    æ±Łæ¹ĸ
    0.25
    egan
    0.25
    eam
    0.24
    archy
    0.24
    çµĦ
    0.24
    Activations Density 0.110%

    No Known Activations