© 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. 1684
    Prev
    Next
    INDEX
    Explanations

    to explore or need to

    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
     rough
    -0.08
     Dominion
    -0.08
     sino
    -0.08
    èĢĨ
    -0.08
    Domin
    -0.08
    ä¼´
    -0.08
     Basics
    -0.08
    ALLY
    -0.08
    å¹²èĦĨ
    -0.07
    á¹Ń
    -0.07
    POSITIVE LOGITS
    lus
    0.11
    kits
    0.10
    èµŀåĬ©
    0.10
    çļĦ人éĥ½
    0.10
    olis
    0.10
    å®īåħ¨ä¿Ŀéļľ
    0.09
    åŀ¢
    0.09
    æįIJ款
    0.09
    åıĸåĨ³
    0.09
    ç²Ĵ
    0.09
    Activations Density 0.034%

    No Known Activations