© 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. 54079
    Prev
    Next
    INDEX
    Explanations

    have a or 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
    ober
    -0.10
    æĿľç»Ŀ
    -0.09
    çıŃ
    -0.09
    ÑģÑĥ
    -0.09
    tram
    -0.09
     Devils
    -0.09
     ÑģÑĤÑĢа
    -0.09
    ç¿ĺ
    -0.08
    éĺµ
    -0.08
    clo
    -0.08
    POSITIVE LOGITS
    å°±è¡Į
    0.09
     пÑĢоÑĦеÑģÑģиона
    0.09
    æĬĬèĩªå·±çļĦ
    0.09
    .deepcopy
    0.09
    æ¸ħæ´Ĺ
    0.09
    åį°
    0.09
    çĶĦ
    0.08
    åŃIJå¼Ł
    0.08
    åģļ
    0.08
    笼
    0.08
    Activations Density 0.048%

    No Known Activations