© 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. 23334
    Prev
    Next
    INDEX
    Explanations

    addition or mixing liquids

    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
    大家åĪĨ享
    -0.10
     Baz
    -0.10
    PIX
    -0.09
    ç§Ģ丽
    -0.09
    丰
    -0.09
     Cock
    -0.09
    骧
    -0.09
    maal
    -0.09
    å¹´ä¹ĭ
    -0.09
    åĿĩçĶ±
    -0.09
    POSITIVE LOGITS
    åĬłåħ¥
    0.12
    åĬłåħ¥äºĨ
    0.10
    Adding
    0.09
    ÐĶобав
    0.09
    å¼ķåħ¥
    0.09
    æ·»åĬł
    0.09
    éĺ²æݧ
    0.09
    ccount
    0.09
    ibil
    0.09
     adm
    0.08
    Activations Density 0.090%

    No Known Activations