© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62907
    Prev
    Next
    INDEX
    Explanations

    tease or coax

    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
    interop
    -0.09
    asy
    -0.08
    Ñģ
    -0.08
    uard
    -0.08
    ital
    -0.08
    yard
    -0.08
    -tm
    -0.08
    stüt
    -0.08
    aight
    -0.08
    istrate
    -0.08
    POSITIVE LOGITS
    ingly
    0.12
    èĸľ
    0.12
    Ī
    0.10
    æĪIJå°±æĦŁ
    0.10
    çİ©èĢį
    0.09
    å©Ģ
    0.09
    å«Ķ
    0.09
    ä½Ĩä»İ
    0.09
    离å¼ĢäºĨ
    0.09
    åĩºäºĨ
    0.09
    Activations Density 0.012%

    No Known Activations