© 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. 23231
    Prev
    Next
    INDEX
    Explanations

    verbs followed by to

    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
    è²Ŀ
    -0.09
    èĭ«
    -0.08
    å»ī
    -0.08
    æīįæľī
    -0.08
    æĶ¾åģĩ
    -0.08
    7
    -0.08
    æīįçŁ¥éģĵ
    -0.08
    éķ¿éĢĶ
    -0.08
    åı¯çĶ¨äºİ
    -0.08
    çĶ©
    -0.08
    POSITIVE LOGITS
    ä¹Łä¸įæĥ³
    0.10
    iou
    0.10
    è¦ģ
    0.10
    æĮģå¹³
    0.10
    è¦ĥ
    0.09
    igor
    0.09
    åŀŃ
    0.09
     to
    0.09
    à¸Ķา
    0.09
    æĩĴå¾Ĺ
    0.09
    Activations Density 0.142%

    No Known Activations