© 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. 19912
    Prev
    Next
    INDEX
    Explanations

    family and parental relationships

    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
    ä½IJ
    -0.10
    ä¹¾åĿ¤
    -0.10
    æĢİä¹Īçľĭ
    -0.10
    æľªæĪIJå¹´
    -0.09
    çİĭåŃIJ
    -0.09
    æ¯ĶåĪĨ
    -0.09
    人çī©
    -0.09
    诽
    -0.09
     intermedi
    -0.09
    rame
    -0.09
    POSITIVE LOGITS
    è¾Ľ
    0.10
    ç»Ļä»ĸ们
    0.10
    9
    0.10
     LENG
    0.09
    ç»ĻåŃ©åŃIJ
    0.09
    æī§æķĻ
    0.09
    为åħ¶
    0.09
    LTR
    0.09
    -popup
    0.09
    7
    0.09
    Activations Density 0.113%

    No Known Activations