© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8741
    Prev
    Next
    INDEX
    Explanations

    find followed by it or that

    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
    人æ°ijæľįåĬ¡
    -0.10
    æįIJçĮ®
    -0.10
    çľ¼æ³ª
    -0.10
    èĹIJ
    -0.09
     sour
    -0.09
    TypeEnum
    -0.09
    ë§Ŀ
    -0.09
    åľ¨éĤ£éĩĮ
    -0.09
    åĴĮæľįåĬ¡
    -0.09
    å¤Ļ
    -0.09
    POSITIVE LOGITS
    gard
    0.09
    apol
    0.09
    åłĤ
    0.08
    ToFront
    0.08
    è¹²
    0.08
    asar
    0.08
     walker
    0.08
    imes
    0.08
    è§Ħå¾ĭ
    0.08
    adt
    0.08
    Activations Density 0.035%

    No Known Activations