© 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. 10000
    Prev
    Next
    INDEX
    Explanations

    latest news or updates

    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
    éĻ¤å¤ĸ
    -0.09
    åĵªæĢķæĺ¯
    -0.08
    5
    -0.08
    åľ¨éĤ£éĩĮ
    -0.08
    æĭį
    -0.08
    å¾ĪæŃ£å¸¸
    -0.08
    4
    -0.08
    2
    -0.08
    æīĢåľ¨
    -0.08
    åķµ
    -0.07
    POSITIVE LOGITS
    eyJ
    0.10
    RICS
    0.09
    ằm
    0.09
    fcn
    0.09
    agi
    0.09
    ä½ľåĵģåĨħ容
    0.09
    ún
    0.09
    vinc
    0.08
    asca
    0.08
    esser
    0.08
    Activations Density 0.370%

    No Known Activations