© 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. 33213
    Prev
    Next
    INDEX
    Explanations

    defending or reigning champions

    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
    äºĨä¸Ģ份
    -0.10
     boyc
    -0.09
    æ¼ł
    -0.09
    éĩįæķ´
    -0.09
    积æŀģæİ¨è¿Ľ
    -0.08
    ä¸įèī¯
    -0.08
    æģ¶
    -0.08
    enge
    -0.08
    çĽĨåľ°
    -0.08
    ixa
    -0.08
    POSITIVE LOGITS
    èī°
    0.09
    verter
    0.09
    串
    0.08
    广éĺĶ
    0.08
    èij³
    0.08
    为åħ¶
    0.08
    utra
    0.08
    edis
    0.08
    å¥Ĺè·¯
    0.08
    éºĭ
    0.08
    Activations Density 0.002%

    No Known Activations