© 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. 8151
    Prev
    Next
    INDEX
    Explanations

    sale of

    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¦
    -0.11
    æįIJçĮ®
    -0.10
    å¥ij
    -0.10
    ampoo
    -0.10
    第äºĮç§į
    -0.09
    èĩªåıij
    -0.09
    bour
    -0.09
    é¢ľ
    -0.08
    èĩªæĦ¿
    -0.08
    è¿ľå¤Ħ
    -0.08
    POSITIVE LOGITS
    éĥ¨åĪĨåĨħ容
    0.10
    ä¸Ģéĥ¨åĪĨ
    0.10
    çļĦä¸Ģéĥ¨åĪĨ
    0.09
    éĥ¨åĪĨ
    0.09
    angi
    0.08
     Angela
    0.08
    ä»įåľ¨
    0.08
    ownership
    0.08
     excess
    0.08
    èįĴ
    0.08
    Activations Density 0.037%

    No Known Activations