© 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. 50753
    Prev
    Next
    INDEX
    Explanations

    button front; battery; telephone

    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
    gend
    -0.09
    igator
    -0.09
    客æĪ·æıIJä¾Ľ
    -0.09
    igators
    -0.09
    gers
    -0.09
    åħļå§Ķ
    -0.09
    æ²¥
    -0.08
     nors
    -0.08
    thest
    -0.08
    èµłéĢģ
    -0.08
    POSITIVE LOGITS
    atura
    0.09
    éŁŃ
    0.09
    ä¸īåĪĨ
    0.09
    nect
    0.09
     ÑĦакÑĤ
    0.09
    å¼ı
    0.09
    çijķçĸµ
    0.09
    äºĭå®ŀ
    0.09
    æ·ĸ
    0.08
     Arbor
    0.08
    Activations Density 0.022%

    No Known Activations