© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3063
    Prev
    Next
    INDEX
    Explanations

    weakness courage evasion chicken major

    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
    çİ©
    -0.09
     ÑģмÑĭÑģл
    -0.09
    ä¸ĢæĬ¹
    -0.09
    zed
    -0.09
    è¿Ļä½į
    -0.08
    åıªä¸įè¿ĩ
    -0.08
    è¿Ļåıª
    -0.08
    orn
    -0.08
    embre
    -0.08
    ä¿®åħ»
    -0.08
    POSITIVE LOGITS
    ly
    0.09
    ful
    0.09
    å®ķ
    0.09
    legg
    0.09
     mutil
    0.08
    鬣
    0.08
    عز
    0.08
    è·»
    0.08
    è¿ĽåĨĽ
    0.08
    Brains
    0.08
    Activations Density 0.011%

    No Known Activations