© 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. 5338
    Prev
    Next
    INDEX
    Explanations

    goes out 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
    ogue
    -0.09
    åıįæŃ£
    -0.08
    æĪIJéķ¿
    -0.08
     fac
    -0.08
    ç¼Ģ
    -0.08
    éĿ¢èī²
    -0.08
     tá»ĵ
    -0.08
    æ¸ħæī«
    -0.08
    çŀ§
    -0.08
    orc
    -0.08
    POSITIVE LOGITS
     Choir
    0.09
    æĥ³åİ»
    0.09
    èĢĮåĩº
    0.09
     Bosch
    0.09
    æµģåĩº
    0.09
    é»ijé¾Ļ
    0.09
    éĺ²
    0.08
    æĢ¯
    0.08
    SMART
    0.08
    spread
    0.08
    Activations Density 0.040%

    No Known Activations