© 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. 3059
    Prev
    Next
    INDEX
    Explanations

    Ole, le, followed by specific endings

    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
    <decltype
    -0.10
    GBT
    -0.09
    为æŃ¢
    -0.09
    沫
    -0.09
    æ·±å±Ĥ
    -0.09
    аÑģÑģ
    -0.09
    ç»Ģ
    -0.09
    matic
    -0.09
    æºĸ
    -0.08
    ä¸Ģ大æī¹
    -0.08
    POSITIVE LOGITS
    æ¹ĵ
    0.09
    istory
    0.08
    æĹ¶å¸¸
    0.08
    UNG
    0.08
    Ľå»º
    0.08
    zelf
    0.08
    ÑģÑĤвеннÑĭе
    0.08
    icao
    0.08
    æ±īåŃĹ
    0.08
    upo
    0.08
    Activations Density 0.008%

    No Known Activations