© 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. 31931
    Prev
    Next
    INDEX
    Explanations

    found that

    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
     early
    -0.10
    ä»ĸå·²ç»ı
    -0.09
    çĶ¨èĩªå·±çļĦ
    -0.09
    æĹ©æľŁ
    -0.09
    ä¸įæĸŃåıijå±ķ
    -0.09
    游
    -0.09
    æĪijå·²ç»ı
    -0.09
    对åħ¶è¿Ľè¡Į
    -0.08
    imet
    -0.08
    íĮĶ
    -0.08
    POSITIVE LOGITS
    ç»ĵæŀľæĺ¾ç¤º
    0.15
    ç»ĵ论
    0.12
     findings
    0.12
    å¾Ĺåĩº
    0.11
    ç»ĵæŀľ
    0.11
    æĦıå¤ĸ
    0.11
    æĥĬ人
    0.10
    åIJĥæĥĬ
    0.10
     surprising
    0.10
     results
    0.10
    Activations Density 0.140%

    No Known Activations