© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5628
    Prev
    Next
    INDEX
    Explanations

    tangible and transient concepts

    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
    atile
    -0.08
     insign
    -0.08
    毫ä¸įçĬ¹è±«
    -0.08
     mia
    -0.08
    nor
    -0.08
    奸
    -0.08
     hairs
    -0.08
    åľ¨ä¹İ
    -0.08
    æ½®
    -0.08
    ROLL
    -0.08
    POSITIVE LOGITS
    ç¼¥
    0.12
    -scrollbar
    0.10
    éļĽãģ«
    0.10
    ties
    0.10
    èŃ½
    0.09
    éļĽ
    0.09
    claimer
    0.09
     beings
    0.09
    æ°Ķæģ¯
    0.08
     اÙĦجÙħع
    0.08
    Activations Density 0.012%

    No Known Activations