© 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. 86729
    Prev
    Next
    INDEX
    Explanations

    of

    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
    é»ŀ
    -0.28
     ringing
    -0.26
     Added
    -0.25
    atable
    -0.24
     möglich
    -0.24
    骡
    -0.24
     CPL
    -0.23
     Buildings
    -0.23
     ideal
    -0.23
    ideal
    -0.23
    POSITIVE LOGITS
    osti
    0.31
    DUCT
    0.29
    澳大
    0.28
    æ·Ģ
    0.28
    prés
    0.27
    osis
    0.27
    ড
    0.26
    åĩºéģĵ
    0.26
    elijke
    0.26
    éģĩåĪ°
    0.25
    Activations Density 0.025%

    No Known Activations