© 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. 10581
    Prev
    Next
    INDEX
    Explanations

    substitute for

    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
    çī¹ä»·
    -0.10
    oking
    -0.09
    acas
    -0.09
    å¸ĮæľĽèĩªå·±
    -0.08
    åĬłåĽº
    -0.08
    éĻĨ
    -0.08
    æī¬
    -0.08
    noinspection
    -0.08
    лав
    -0.08
    reuse
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.12
    ä¸įäºĨ
    0.10
    èĢĮæĺ¯
    0.10
    æľīä¸Ģä½į
    0.09
    ä¸ĢæĿ¯
    0.09
     radial
    0.09
    åĽ¹
    0.09
    aten
    0.09
    oder
    0.08
    å°±åľ¨äºİ
    0.08
    Activations Density 0.006%

    No Known Activations