© 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. 56070
    Prev
    Next
    INDEX
    Explanations

    to say the least

    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
    åīĬ
    -0.09
    æ»ĵ
    -0.08
    dg
    -0.08
    åķ¡
    -0.08
     dissip
    -0.08
     dissert
    -0.08
    æīĢè°ĵçļĦ
    -0.08
    aurant
    -0.08
     gu
    -0.08
     dagger
    -0.08
    POSITIVE LOGITS
    ç¡ĸ
    0.09
    éĿ¢åŃIJ
    0.09
    åı¸
    0.09
    æķ´ä¸ª
    0.09
    æľºåħ³
    0.09
     Entire
    0.09
    çĦ°
    0.08
    åŁºæľ¬æĥħåĨµ
    0.08
    åıĸæļĸ
    0.08
    åĨ·èĹı
    0.08
    Activations Density 0.008%

    No Known Activations