© 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. 19201
    Prev
    Next
    INDEX
    Explanations

    quest for

    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
    çĮ·
    -0.10
    åľ¨çݩ家
    -0.09
    æ¶Įçİ°
    -0.09
    å·¥ä½ľæľºåĪ¶
    -0.09
    æł·åŃIJ
    -0.09
    éĿ¡
    -0.08
    åıĪ称
    -0.08
    稳
    -0.08
    è§īéĨĴ
    -0.08
    å®ĮåĸĦçļĦ
    -0.08
    POSITIVE LOGITS
     quest
    0.16
    追æ±Ĥ
    0.13
     pursuit
    0.13
     journey
    0.13
    寻æī¾
    0.13
     efforts
    0.12
     Suche
    0.12
    追寻
    0.11
    jour
    0.11
     hunt
    0.11
    Activations Density 0.283%

    No Known Activations