© 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. 88083
    Prev
    Next
    INDEX
    Explanations

    periods

    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
    eme
    -0.30
    passes
    -0.28
    emes
    -0.26
    HostException
    -0.25
    çĽijäºĭä¼ļ
    -0.25
    telegram
    -0.25
    lashes
    -0.25
    åľºä¸Ĭ
    -0.24
    GREE
    -0.24
    讨åİĮ
    -0.24
    POSITIVE LOGITS
    izador
    0.27
    mund
    0.25
    rador
    0.25
    秫
    0.24
    nad
    0.24
     likewise
    0.24
    æ¯ĭ
    0.24
     kaps
    0.24
    enn
    0.23
    ä¸įåIJĥ
    0.23
    Activations Density 0.003%

    No Known Activations