© 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. 19253
    Prev
    Next
    INDEX
    Explanations

    glimpse into / insight into

    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
    念
    -0.09
    æݧ
    -0.08
    åijĬè¯ī
    -0.08
    ame
    -0.08
    æĦŁè§īèĩªå·±
    -0.08
    è§ľ
    -0.08
    åħ¬åijĬ
    -0.08
     curious
    -0.08
    æĮĩåįĹ
    -0.08
     инÑĤеÑĢнеÑĤ
    -0.08
    POSITIVE LOGITS
    çĤ¹äºĨ
    0.10
    为åķ¥
    0.10
    æ·±å¤Ħ
    0.09
     recess
    0.09
    enumer
    0.09
    éļ¾å¿ĺ
    0.08
    缼å¼Ģ
    0.08
     future
    0.08
    ç´«å¤ĸ
    0.08
    为ä»Ģä¹Ī
    0.08
    Activations Density 0.026%

    No Known Activations