© 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. 18881
    Prev
    Next
    INDEX
    Explanations

    enables, allows, offers

    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
    çĥŃéĹ¹
    -0.10
    æĺĻ
    -0.09
     nơi
    -0.09
    å¼Ħ
    -0.08
    ä¸įåIJĪéĢĤ
    -0.08
    çŀŃ解
    -0.08
    åħļåĴĮ
    -0.08
    å°±æĺ¯ä¸ºäºĨ
    -0.08
    æ¯Ķè¾ĥç®Ģåįķ
    -0.08
    åıij声
    -0.08
    POSITIVE LOGITS
    大å¹ħæıIJåįĩ
    0.16
    大å¹ħ度
    0.15
    大å¹ħ
    0.13
     superior
    0.11
    大大æıIJé«ĺ
    0.11
    ä¸įä»ħ
    0.10
    å¼ĢåĪĽ
    0.10
    ãģĹãģĭãĤĤ
    0.10
    åħĭæľį
    0.09
    ä¸ļåĨħ
    0.09
    Activations Density 0.334%

    No Known Activations