© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129833
    Prev
    Next
    INDEX
    Explanations

    royalty

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çİ°åľ¨å·²ç»ı
    -0.26
    elsen
    -0.24
     Morm
    -0.24
    èĢĮçİ°åľ¨
    -0.24
    SCORE
    -0.23
    -present
    -0.23
    datable
    -0.23
    reuse
    -0.23
     clap
    -0.22
    inged
    -0.22
    POSITIVE LOGITS
    ove
    0.30
    illin
    0.26
     Wol
    0.24
    lover
    0.24
     shadow
    0.23
     Peak
    0.23
    licher
    0.23
    们
    0.23
    ces
    0.23
    iloc
    0.23
    Activations Density 0.083%

    No Known Activations