© 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. 111651
    Prev
    Next
    INDEX
    Explanations

    AK

    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
    çݩ家æĿ¥è¯´
    -0.26
     zug
    -0.25
    ä¸įæĿ¥
    -0.25
     action
    -0.25
    lar
    -0.25
    ycz
    -0.24
    æĺ¯åIJ¦ä¼ļ
    -0.24
    ieten
    -0.24
    azel
    -0.24
     Check
    -0.24
    POSITIVE LOGITS
    ndon
    0.27
    æĪij们çļĦ
    0.25
    -letter
    0.25
    iffin
    0.24
    æĭĦ
    0.24
    çĮ·
    0.24
    让æĪij们
    0.23
    Segment
    0.23
    ç´¯
    0.23
    .ceil
    0.23
    Activations Density 0.001%

    No Known Activations