© 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. 54799
    Prev
    Next
    INDEX
    Explanations

    food items ending in 's' or 'ies'

    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
    chaft
    -0.09
    æ´Ĺæīĭ
    -0.09
    æĢı
    -0.09
    ä¸įæľį
    -0.09
    åŀĥåľ¾æ¡¶
    -0.09
    vrier
    -0.09
    roulette
    -0.08
    _PACKAGE
    -0.08
    Laugh
    -0.08
    ä¸įæĺİ
    -0.08
    POSITIVE LOGITS
    åĴĮæľįåĬ¡
    0.10
    æĮĩå°ĸ
    0.09
    çī¹åĪ«
    0.08
    éĩijåŃĹ
    0.08
    æľĶ
    0.08
    IELDS
    0.07
    åŃIJéĩĮ
    0.07
    pheres
    0.07
    ÄĻ
    0.07
     WITH
    0.07
    Activations Density 0.025%

    No Known Activations