© 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. 20023
    Prev
    Next
    INDEX
    Explanations

    outer parts or surfaces

    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
    bens
    -0.09
    éģį
    -0.09
    åĽłä¸ºåľ¨
    -0.09
    åľ°ä¸ĭ
    -0.09
    éĻŁ
    -0.08
     Wah
    -0.08
     hızlı
    -0.08
    åĪ°äºĨ
    -0.08
    æ±Łæ¹ĸ
    -0.08
    ç²ī
    -0.08
    POSITIVE LOGITS
    aviest
    0.09
    éĥ¨ä»½
    0.09
    å±ĤéĿ¢
    0.09
     portion
    0.09
    deer
    0.09
    éĥ¨åĪĨ
    0.08
    _interface
    0.08
    Ctx
    0.08
     Suspension
    0.08
    oose
    0.08
    Activations Density 0.608%

    No Known Activations