© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88639
    Prev
    Next
    INDEX
    Explanations

    time/sequence

    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
    没æľīå¿ħè¦ģ
    -0.39
    ä¸įåģļ
    -0.28
    æīĢ以æĪij
    -0.28
    ubb
    -0.27
    anya
    -0.27
    ä¸įåºĶ该
    -0.26
    ä¸įè¦ģåĨį
    -0.26
    :type
    -0.26
    ä¸įè¦ģ
    -0.26
    éģ¿åħį
    -0.25
    POSITIVE LOGITS
     stimulated
    0.27
    积
    0.26
     adipisicing
    0.26
    Ŀå§ĭ
    0.25
    ocode
    0.25
    jur
    0.24
    åıĸå¾Ĺ
    0.24
    spec
    0.23
    YLE
    0.23
    å§ĭ
    0.23
    Activations Density 0.001%

    No Known Activations