© 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. 22-TRANSCODER-HP
    7. 99187
    Prev
    Next
    INDEX
    Explanations

    technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    UMB
    -0.27
     sıra
    -0.26
    umb
    -0.26
    à¸Ľà¸£à¸°à¹Ĥยà¸Ĭà¸Ļ
    -0.25
    ume
    -0.25
     thôi
    -0.25
    uin
    -0.25
     certain
    -0.24
    æŁIJäºĽ
    -0.24
    fiber
    -0.24
    POSITIVE LOGITS
    eil
    0.28
    ``↵
    0.27
    代åĬŀ
    0.24
    _parsed
    0.24
     extrad
    0.23
    SplitOptions
    0.23
    éģ¨
    0.23
    entral
    0.23
     trav
    0.23
     pcs
    0.23
    Activations Density 0.021%

    No Known Activations