© 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. 5723
    Prev
    Next
    INDEX
    Explanations

    Congress actions

    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
    ç¾İ人
    -0.10
    ä¾Ĩèĩª
    -0.10
    æĿ¥èĩª
    -0.09
    orm
    -0.09
    渺
    -0.08
    äºĭä¸ļåıijå±ķ
    -0.08
    aits
    -0.08
    çİ·
    -0.08
    广éĺĶçļĦ
    -0.08
    人çĶŁçļĦ
    -0.08
    POSITIVE LOGITS
    ional
    0.10
    æĩĴ
    0.09
    çļĦä¸Ģ项
    0.09
    æĪIJåĬŁ
    0.09
    ðŁı»
    0.08
    Sanders
    0.08
    lav
    0.08
    çŃīéĥ¨éŨ
    0.08
    -led
    0.08
    .timedelta
    0.08
    Activations Density 0.012%

    No Known Activations