© 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. 38493
    Prev
    Next
    INDEX
    Explanations

    office Location or department

    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
    ä½ı
    -0.10
    æ¯įæł¡
    -0.10
    InstanceOf
    -0.09
    该éĻ¢
    -0.09
    IMS
    -0.09
    å½Ģ
    -0.09
    æĽ¦
    -0.09
    壤
    -0.09
    è·¯è¿ĩ
    -0.09
    ignment
    -0.08
    POSITIVE LOGITS
    hm
    0.09
    holder
    0.09
    hol
    0.09
    æŀ¯
    0.08
    umen
    0.08
    оÑĢÑĤ
    0.08
    çijĻ
    0.08
    ga
    0.08
    utm
    0.08
     hÃłnh
    0.08
    Activations Density 0.030%

    No Known Activations