© 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. 9135
    Prev
    Next
    INDEX
    Explanations

    do, doing, did

    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
    æ³Ľ
    -0.10
    çļĦéĴ±
    -0.09
    æĮĿ
    -0.09
    даÑĩи
    -0.09
    ooks
    -0.09
    æŃ£åĵģ
    -0.09
    çĶŃ
    -0.09
     Lage
    -0.09
    èĪ´
    -0.09
    æµĴ
    -0.08
    POSITIVE LOGITS
    åıĺéĿ©
    0.09
    æĶ¹åıĺ
    0.09
    estroy
    0.08
    sad
    0.08
    etto
    0.08
    举åĬ¨
    0.08
    sink
    0.08
    交éĶĻ
    0.08
    _rl
    0.08
    举æݪ
    0.08
    Activations Density 0.048%

    No Known Activations