© 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. 53197
    Prev
    Next
    INDEX
    Explanations

    chief of

    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
     ׾×Ĺ
    -0.09
    LOSS
    -0.09
    èĢģ人家
    -0.09
    roach
    -0.09
    缮çļĦæĺ¯
    -0.09
    åĨ³å®ļ
    -0.09
    è¿Ļ件äºĭæĥħ
    -0.08
    åıĤ
    -0.08
    æ±Łå±±
    -0.08
     Flux
    -0.08
    POSITIVE LOGITS
    åij½è¿IJ
    0.11
    幸
    0.10
    ä¸Ģç»Ħ
    0.09
    orra
    0.09
    èįĴ
    0.08
    é£İæĥħ
    0.08
    adies
    0.08
    ä¸Ģ个å°ı
    0.08
    ooks
    0.08
     ÑģвÑıзи
    0.08
    Activations Density 0.008%

    No Known Activations