© 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. 112913
    Prev
    Next
    INDEX
    Explanations

    lamb

    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
    Negative Logits
    éĻĢ
    -0.27
    íĮħ
    -0.26
     ench
    -0.25
     sidel
    -0.25
    ®
    -0.24
    åİŁå§ĭ
    -0.24
    ç¦ģ
    -0.23
    ?id
    -0.23
    ä¸į平衡
    -0.23
    ctic
    -0.23
    POSITIVE LOGITS
    ellar
    0.25
    .DESC
    0.25
    éĶĪ
    0.24
    Rib
    0.24
    YES
    0.23
    è´¶
    0.23
    ç»Ŀ
    0.23
     Rib
    0.23
     priesthood
    0.23
    SON
    0.22
    Activations Density 0.092%

    No Known Activations