© 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. 25-TRANSCODER-HP
    7. 109426
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    cly
    -0.30
    åİĦ
    -0.27
     vip
    -0.26
    夺
    -0.25
    -ste
    -0.25
    è¿Ľç¨ĭä¸Ń
    -0.24
     VIP
    -0.24
    ç¬¬åĽĽå±Ĭ
    -0.24
    ascus
    -0.24
     wired
    -0.23
    POSITIVE LOGITS
    è´·
    0.30
    etch
    0.29
    èĦı
    0.28
    åİĿ
    0.27
    ãĤĪãģĨãģ«ãģªãģ£ãģŁ
    0.25
    coh
    0.25
    geries
    0.25
    EH
    0.24
    çŃĸ
    0.24
    çıŃåŃIJ
    0.24
    Activations Density 0.981%

    No Known Activations