© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10206
    Prev
    Next
    INDEX
    Explanations

    nude or naked contexts

    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
    ingly
    -0.09
    åħħåĪĨåĪ©çĶ¨
    -0.08
    olen
    -0.08
     fodder
    -0.08
    iane
    -0.08
    帰ãĤĬ
    -0.08
    ä¸Ģæ³¢
    -0.08
    STM
    -0.08
     Lonely
    -0.08
    æĺİçŁ¥
    -0.08
    POSITIVE LOGITS
    -ish
    0.11
    launch
    0.09
    cul
    0.09
    eger
    0.09
    æ±Łåİ¿
    0.08
    èĩĥ
    0.08
    å¸Ĥåľºç«ŀäºī
    0.08
    gens
    0.08
    ï¸
    0.08
    åĬłä¸Ĭ
    0.08
    Activations Density 0.007%

    No Known Activations