© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21553
    Prev
    Next
    INDEX
    Explanations

    Browns owner or Brownsburg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eam
    -0.11
    eenth
    -0.10
    夥
    -0.10
    idor
    -0.09
    ÙĨÙī
    -0.09
    emens
    -0.09
    emin
    -0.09
    åĩĨç¡®
    -0.09
    æĸ°è¥¿
    -0.09
    çĻ½éĽª
    -0.08
    POSITIVE LOGITS
    ish
    0.14
    lee
    0.10
    ie
    0.09
    pace
    0.09
    field
    0.09
    estone
    0.09
    æ¦Ī
    0.09
    ice
    0.09
    pth
    0.08
    less
    0.08
    Activations Density 0.002%

    No Known Activations