© 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. 5967
    Prev
    Next
    INDEX
    Explanations

    exploration and discovery

    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
    ioned
    -0.11
    _hooks
    -0.10
    inel
    -0.09
    irmed
    -0.09
    ç»ĩ
    -0.09
    loth
    -0.08
    å®ŀæķĪ
    -0.08
    аÑİÑĤÑģÑı
    -0.08
    éªĹ
    -0.08
    åŃIJåŃĻ
    -0.08
    POSITIVE LOGITS
    æݢ索
    0.16
     exploration
    0.14
     explore
    0.13
     Exploration
    0.12
    æľªçŁ¥
    0.11
     Explore
    0.11
     explored
    0.11
    Explore
    0.10
     exploring
    0.10
     discovery
    0.10
    Activations Density 0.032%

    No Known Activations