© 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. 36187
    Prev
    Next
    INDEX
    Explanations

    voting and ballots

    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
    æķŀ
    -0.10
    éĺ»åĬĽ
    -0.10
    ëĦ
    -0.09
    entifier
    -0.09
    weep
    -0.09
    çĹ°
    -0.09
    å°ıæĻĤ
    -0.09
    笥
    -0.09
    åħ±éĿĴåĽ¢
    -0.09
    HELL
    -0.09
    POSITIVE LOGITS
    ä¸Ģå¼ł
    0.09
    åŁĭ
    0.08
    æĹ©æĹ¥
    0.08
    å¥İ
    0.08
    icap
    0.08
    acho
    0.08
    ä¸Ģäºĭ
    0.08
    梢
    0.08
     Internet
    0.08
    æĬij
    0.08
    Activations Density 0.002%

    No Known Activations