© 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. 98891
    Prev
    Next
    INDEX
    Explanations

    Contains many numbers

    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
    ovsky
    -0.27
    innie
    -0.26
    .FC
    -0.26
    iors
    -0.25
    Extras
    -0.25
    ï¼ģ",
    -0.24
    own
    -0.23
     attrs
    -0.23
    ki
    -0.23
    astos
    -0.23
    POSITIVE LOGITS
    çİĩ为
    0.26
    客è§Ĥ
    0.25
    äºĨä¸Ģåľº
    0.24
    æīĢè°ĵ
    0.24
    ...↵
    0.24
     tras
    0.24
    交éĢļå®īåħ¨
    0.24
    èĥ¥
    0.23
     ere
    0.23
     enter
    0.23
    Activations Density 0.001%

    No Known Activations