© 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. 33136
    Prev
    Next
    INDEX
    Explanations

    nominal, Star, rapid, donation, ospel Hill

    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
    zek
    -0.09
    åĿIJä¸ĭ
    -0.09
     agg
    -0.09
    xDF
    -0.09
    xCD
    -0.09
    嵬
    -0.09
     PROF
    -0.09
    unte
    -0.09
    ftype
    -0.09
     unt
    -0.09
    POSITIVE LOGITS
    utan
    0.08
    è´¨éĩıå®īåħ¨
    0.08
    æ¼Ĩ
    0.08
    éĵ£
    0.08
    ç¾ļ
    0.08
     undergo
    0.08
    æĪĹ
    0.08
    åİ
    0.08
     nominal
    0.08
    å¤©åľ°
    0.08
    Activations Density 0.046%

    No Known Activations