© 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. 87150
    Prev
    Next
    INDEX
    Explanations

    Units of time

    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
    åį°ç«ł
    -0.27
     slee
    -0.26
    ä¸į代表
    -0.25
    齿
    -0.24
    æļĸæ°Ķ
    -0.24
    tright
    -0.23
    OrUpdate
    -0.23
    eya
    -0.23
     sense
    -0.23
     legality
    -0.23
    POSITIVE LOGITS
    -thirds
    0.30
    åħĴ
    0.25
    ÑģÑĤо
    0.24
    åĦ¿
    0.24
    agt
    0.24
    .sup
    0.23
    fit
    0.23
    shed
    0.23
    edly
    0.23
    Soon
    0.23
    Activations Density 0.062%

    No Known Activations