© 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. 11324
    Prev
    Next
    INDEX
    Explanations

    double, ray, puffy, class, SA

    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
    çķĮ
    -0.10
    ç¼´è´¹
    -0.09
    ç§Łè½¦
    -0.09
    çħ®
    -0.09
    为ä»Ģä¹Īä¸į
    -0.08
    brew
    -0.08
    å®°
    -0.08
    пеÑĩаÑĤ
    -0.08
    å¥¹åľ¨
    -0.08
    vell
    -0.08
    POSITIVE LOGITS
    èĬ±çĵ£
    0.10
     пÑĢоÑĤ
    0.09
    ä»Ĺ
    0.09
    ä¸Ĭå¸Ĥ
    0.09
    ckeditor
    0.09
     ÙĪاÙĦاست
    0.08
    UME
    0.08
    éĻĢ
    0.08
    丹
    0.08
    èµļ
    0.08
    Activations Density 0.095%

    No Known Activations