© 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. 7602
    Prev
    Next
    INDEX
    Explanations

    temperature range

    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
    mund
    -0.09
    å®ŀäºĭæ±Ĥæĺ¯
    -0.09
    åĩłåįģå¹´
    -0.09
    é»Ħèī²
    -0.09
    clid
    -0.09
    çĦľ
    -0.09
    å®ŀä¹łçĶŁ
    -0.09
    èIJĥ
    -0.08
    çļĦçIJĨ念
    -0.08
    笼
    -0.08
    POSITIVE LOGITS
    èıı
    0.10
    è´Ń
    0.10
    æĢģ
    0.10
    åĪ¸
    0.09
    ulpt
    0.09
    èĵ¬
    0.09
    egg
    0.09
     australia
    0.08
    çŁ³èĨı
    0.08
    èĬľ
    0.08
    Activations Density 0.057%

    No Known Activations