© 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. 52978
    Prev
    Next
    INDEX
    Explanations

    Firefox browser

    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
    æĻ®
    -0.10
    æĬ½åıĸ
    -0.09
    æĮijè¡ħ
    -0.09
    art
    -0.09
    ÑģÑĤи
    -0.09
    plement
    -0.09
    æ³»
    -0.09
    ç°¸
    -0.09
     возд
    -0.08
    agr
    -0.08
    POSITIVE LOGITS
    æľįä»İ
    0.11
    说æĺ¯
    0.09
    çĶŁçĶŁ
    0.09
    åŃIJå¼¹
    0.09
    бÑĢа
    0.09
    нд
    0.09
    perse
    0.09
    æµıè§ĪåĻ¨
    0.08
    uges
    0.08
     ----------------------------------------------------------------------------↵
    0.08
    Activations Density 0.049%

    No Known Activations