© 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. 20262
    Prev
    Next
    INDEX
    Explanations

    extent to which

    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
    éªļ
    -0.09
    è§īå¾Ĺå¾Ī
    -0.09
    åŁºæķ°
    -0.08
    宵
    -0.08
    Lng
    -0.08
    ery
    -0.08
    æijħ
    -0.08
     foam
    -0.08
    аÑĨи
    -0.08
    èķĥ
    -0.08
    POSITIVE LOGITS
     manner
    0.13
    arez
    0.12
     обÑĢазом
    0.10
    é¢ĺ主
    0.10
    éħ¬
    0.09
    ãģĨãģ¡ãģ«
    0.09
    æĸ¹å¼ı
    0.09
     way
    0.09
    æŶåĢĻ
    0.09
    ä»»ä½ķæŶåĢĻ
    0.09
    Activations Density 0.061%

    No Known Activations