© 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. 27554
    Prev
    Next
    INDEX
    Explanations

    ancillary schedules, auction office, agency

    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
     vig
    -0.10
    çĶŁæ´»çݯå¢ĥ
    -0.08
    åħ³æ³¨åº¦
    -0.08
    สà¸Ķ
    -0.08
    æľįåĬ¡ä¸Ńå¿ĥ
    -0.08
    alone
    -0.08
     chaining
    -0.08
    FO
    -0.08
    æł¡åĽŃ
    -0.08
    å¾Ĵ
    -0.08
    POSITIVE LOGITS
    å¸Ń
    0.10
    çħ§
    0.10
    ç®Ĺæ³ķ
    0.09
     program
    0.09
    èĮľ
    0.08
    ëĿ¼ëıĦ
    0.08
    éĻIJéĩı
    0.08
    é»İæĺİ
    0.08
    æĭĽåĭŁ
    0.08
    æī©
    0.08
    Activations Density 0.087%

    No Known Activations