© 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. 34065
    Prev
    Next
    INDEX
    Explanations

    list out or list factors

    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
     PARTICULAR
    -0.10
    çļĦä¸ĢéĿ¢
    -0.09
    ulings
    -0.09
    æ°¸ä¹ħ
    -0.09
    essaging
    -0.09
    olean
    -0.09
    æİ¥è¿ij
    -0.08
     воÑĤ
    -0.08
    ÑĪа
    -0.08
    æ¦Ń
    -0.08
    POSITIVE LOGITS
    æľīåĵªäºĽ
    0.14
     reasons
    0.13
     ways
    0.11
    çIJĨçĶ±
    0.11
    说åĩº
    0.11
    çĨ¨
    0.10
    åĪĹ举
    0.10
    åIJįåįķ
    0.10
     Names
    0.10
    åĵªäºĽ
    0.09
    Activations Density 0.133%

    No Known Activations