© 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. 17804
    Prev
    Next
    INDEX
    Explanations

    from or through

    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
    以æѤ
    -0.11
    黯
    -0.10
    åħ±åIJĮä½ĵ
    -0.10
    _cast
    -0.09
    -redux
    -0.09
     Laden
    -0.09
     lastIndex
    -0.09
     ÑĦакÑĤ
    -0.09
    åĢŁæѤ
    -0.09
    ARRIER
    -0.09
    POSITIVE LOGITS
    ç§įç§į
    0.12
    æŁIJç§į
    0.11
     being
    0.11
     having
    0.10
    æĪĸ许æĺ¯
    0.10
    å·²ä¹ħ
    0.10
     lack
    0.10
    ä¹Łè®¸æĺ¯
    0.09
    缺ä¹ı
    0.09
    è¿ijäºĽ
    0.08
    Activations Density 0.121%

    No Known Activations