© 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. 88246
    Prev
    Next
    INDEX
    Explanations

    ,

    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°æľīçļĦ
    -0.26
    æ¸Ĭ
    -0.25
    éĢł
    -0.25
    æīĢæıIJä¾ĽçļĦ
    -0.24
    draw
    -0.24
    对å¤ĸ
    -0.24
    æĬĬèĩªå·±çļĦ
    -0.24
    对人ä½ĵ
    -0.24
    ä¾Ī
    -0.23
    :\\
    -0.23
    POSITIVE LOGITS
     stalking
    0.27
    поÑĢ
    0.25
    éľĩèį¡
    0.25
    _NOW
    0.25
    (ord
    0.24
    füg
    0.24
    秩åºı
    0.24
     noqa
    0.24
    вол
    0.24
     tán
    0.24
    Activations Density 0.014%

    No Known Activations