© 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. 21483
    Prev
    Next
    INDEX
    Explanations

    discuss how to about

    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
    çĸĥ
    -0.08
    tent
    -0.08
    erton
    -0.07
    ä¸ĩ象
    -0.07
    hl
    -0.07
    chem
    -0.07
    èīº
    -0.07
    dent
    -0.07
     flor
    -0.07
    elen
    -0.07
    POSITIVE LOGITS
    èĥ½ä½¿
    0.11
    å¿Ŀ
    0.10
    èĥ½è®©
    0.10
    æIJºæīĭ
    0.10
    èĥ½æ»¡è¶³
    0.09
    æľĢéĢĤåIJĪ
    0.09
    åıĤä¸İåĪ°
    0.09
    <quote
    0.09
    ä¸įè´Ł
    0.09
    åı¯çĶ¨äºİ
    0.09
    Activations Density 0.019%

    No Known Activations