© 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. 87953
    Prev
    Next
    INDEX
    Explanations

    Dates and 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
    Acceleration
    -0.28
    sla
    -0.28
    åIJĦ个çݯèĬĤ
    -0.26
     #:
    -0.26
     erm
    -0.24
    /about
    -0.24
    ä½ľä¸ºä¸Ģ个
    -0.24
     saliva
    -0.23
    ä¹Łæľīå¾Īå¤ļ
    -0.23
     Attend
    -0.23
    POSITIVE LOGITS
    KHR
    0.26
     (()
    0.25
    [âĢ¦
    0.24
    å¥Ń
    0.23
     systematically
    0.23
    ...↵↵
    0.23
    ...↵
    0.23
     finally
    0.23
    ida
    0.23
    DET
    0.22
    Activations Density 0.025%

    No Known Activations