© 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. 98966
    Prev
    Next
    INDEX
    Explanations

    .gov

    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
    ered
    -0.31
    ARA
    -0.30
    æĻ¦
    -0.29
     "@/
    -0.28
    ara
    -0.27
    vester
    -0.26
    erra
    -0.26
     volont
    -0.24
    isclosed
    -0.24
    uele
    -0.24
    POSITIVE LOGITS
    s
    0.28
    sist
    0.26
    sing
    0.26
    scientific
    0.25
    sur
    0.25
    space
    0.25
     holidays
    0.24
    sit
    0.24
    figcaption
    0.24
    sup
    0.24
    Activations Density 0.207%

    No Known Activations