© 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. 109324
    Prev
    Next
    INDEX
    Explanations

    ha

    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
     lég
    -0.29
    ÅĽl
    -0.28
    ogie
    -0.26
    ยà¸Ńà¸Ķ
    -0.26
     dane
    -0.26
    é²ľ
    -0.26
    æļĤç¼ĵ
    -0.25
    nelly
    -0.25
    baugh
    -0.24
    oÄŁlu
    -0.24
    POSITIVE LOGITS
    itable
    0.30
     gained
    0.27
    _gain
    0.24
    ith
    0.24
    uth
    0.24
    oot
    0.23
     regards
    0.23
    åľ»
    0.23
    æĤłä¹ħ
    0.23
    å°Ķ
    0.23
    Activations Density 0.914%

    No Known Activations