© 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. 19695
    Prev
    Next
    INDEX
    Explanations

    legal filings and disclaimers

    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
    æłĹ
    -0.08
     ÐĶмиÑĤÑĢ
    -0.08
    æĦļ
    -0.08
     Murdoch
    -0.08
    å´Ń
    -0.08
    äº
    -0.07
     ÐIJлекÑģан
    -0.07
     sta
    -0.07
    éĵİ
    -0.07
    ened
    -0.07
    POSITIVE LOGITS
    'S
    0.14
    ’S
    0.12
    ean
    0.11
    å®ĭä½ĵ
    0.09
    å½ĵæĪij
    0.09
    åįĩèµ·
    0.09
    /OR
    0.08
    代
    0.08
    eparator
    0.08
    å½ĵä¹ĭ
    0.08
    Activations Density 1.403%

    No Known Activations