© 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. 48388
    Prev
    Next
    INDEX
    Explanations

    Jackie and Jacqueline names

    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
    lessly
    -0.10
    kip
    -0.09
    ality
    -0.09
    acom
    -0.09
    -wife
    -0.08
    iggs
    -0.08
    ðŁı¼
    -0.08
    ices
    -0.08
    ession
    -0.08
    illed
    -0.08
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.10
    íıIJ
    0.09
    cus
    0.09
    ÑĤÑĮÑģÑı
    0.09
    æ©Ľ
    0.09
    ../../../
    0.09
    ron
    0.08
    ourt
    0.08
    人çĶŁçļĦ
    0.08
    udd
    0.08
    Activations Density 0.016%

    No Known Activations