© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20941
    Prev
    Next
    INDEX
    Explanations

    listing items with commas or conjunctions

    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
     Afr
    -0.09
    æĤŃ
    -0.08
    Attrs
    -0.08
    æĭĤ
    -0.08
    ä¸ī家
    -0.08
    å®Ľ
    -0.08
    让å®ĥ
    -0.08
    åĩłç§į
    -0.08
    å°ļ
    -0.08
    èĵ¬
    -0.08
    POSITIVE LOGITS
    adesh
    0.10
    æĹ¥å¸¸çĶŁæ´»
    0.10
    è©
    0.10
    å½ĵåģļ
    0.09
    第ä¸Ģä½į
    0.09
    æīĵå¼ĢäºĨ
    0.09
    æ³ģ
    0.09
    å§ĭç»ĪåĿļæĮģ
    0.09
    çĶļèĩ³æĺ¯
    0.09
    失åĪ©
    0.09
    Activations Density 0.165%

    No Known Activations