© 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. 58651
    Prev
    Next
    INDEX
    Explanations

    Answering questions and providing information

    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
    unter
    -0.10
    被åĬ¨
    -0.09
    pat
    -0.09
    adin
    -0.09
    æĪijä¹Ł
    -0.09
    æĸĹ
    -0.08
    ification
    -0.08
    é©°
    -0.08
    åºĶ该æĢİä¹Ī
    -0.08
    umbo
    -0.08
    POSITIVE LOGITS
    ÑģÑı
    0.10
    ä»¥äººä¸ºæľ¬
    0.10
    以åħ¶
    0.10
    è£ķ
    0.09
    LOOR
    0.09
    oire
    0.09
    вл
    0.09
    éļ¼
    0.09
    ä½ij
    0.08
    ä¸įäºĨ
    0.08
    Activations Density 0.022%

    No Known Activations