© 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. 36646
    Prev
    Next
    INDEX
    Explanations

    separatism and independence

    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
    éŀŃ
    -0.09
    æĻ®æ³ķ
    -0.08
    elow
    -0.08
    åĨ¤
    -0.08
     aval
    -0.08
    ç©¿è¿ĩ
    -0.08
    ä½ĵåĪ¶
    -0.08
    ä½ĵåĪ¶æľºåĪ¶
    -0.08
     cave
    -0.08
    æıŃéľ²
    -0.08
    POSITIVE LOGITS
     separat
    0.12
    åľ°åĮºçļĦ
    0.11
    åľ°åĮº
    0.11
    åĪĨ离
    0.09
    åĴĮåľ°åĮº
    0.09
    çĶĺ
    0.09
    asar
    0.09
     Separ
    0.09
    èĩªæ²»åĮº
    0.09
    çѱ
    0.09
    Activations Density 0.175%

    No Known Activations