© 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. 52967
    Prev
    Next
    INDEX
    Explanations

    dessert or derivative

    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
    -0.12
    ount
    -0.10
    adin
    -0.10
    åİķæīĢ
    -0.09
    书记
    -0.09
    ../
    -0.09
    åŃ£åIJİèµĽ
    -0.09
    же
    -0.08
     اÙĦتجارÙĬØ©
    -0.08
    íĥĿ
    -0.08
    POSITIVE LOGITS
    wards
    0.12
    idge
    0.11
    agger
    0.10
    ault
    0.09
    iqu
    0.09
    å½ĴæĿ¥
    0.09
    Crow
    0.09
    带头人
    0.08
    antt
    0.08
     lover
    0.08
    Activations Density 0.003%

    No Known Activations