© 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. 98146
    Prev
    Next
    INDEX
    Explanations

    show

    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
    ä½łåı¯ä»¥
    -0.29
    ä½łä¸į
    -0.27
    cies
    -0.26
    ä½łèĥ½
    -0.26
    omore
    -0.25
    —you
    -0.24
    ROID
    -0.24
    دÙĬدة
    -0.24
    æī¼
    -0.24
    ä½łä¹Ł
    -0.24
    POSITIVE LOGITS
    容
    0.31
     sm
    0.26
    down
    0.26
    æľŁéĻIJ
    0.25
    sm
    0.25
    骶
    0.24
    (sh
    0.24
    ookie
    0.23
    康å¤į
    0.23
    ARI
    0.23
    Activations Density 0.022%

    No Known Activations