© 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. 31162
    Prev
    Next
    INDEX
    Explanations

    positive and negative outlooks

    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
    çķ¥
    -0.09
    andre
    -0.09
    ä½ľå¼Ĭ
    -0.08
    èĴĻ
    -0.08
     Enumerable
    -0.08
    ler
    -0.08
     invalidate
    -0.08
     pure
    -0.08
    塾
    -0.08
    pure
    -0.07
    POSITIVE LOGITS
    æľªæĿ¥åıijå±ķ
    0.12
    å·²ä¹ħ
    0.10
    æ£īèĬ±
    0.09
    æľªæĿ¥
    0.09
    å¯ŀ
    0.09
    åħ¨å¹´
    0.09
    å·²ä¹ħçļĦ
    0.09
    èĮ§
    0.09
    ä¹ħ
    0.09
    æľªæĿ¥çļĦ
    0.09
    Activations Density 0.021%

    No Known Activations