© 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. 4435
    Prev
    Next
    INDEX
    Explanations

    pizza and related foods

    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
    جد
    -0.09
    åĨħ马
    -0.09
    åįģåŃĹ
    -0.09
    æݸ
    -0.09
     mixins
    -0.09
    _extraction
    -0.09
    åİ©
    -0.08
    ãĢĴ
    -0.08
    ä½ľé£İ
    -0.08
    ä¸ĢåĪĨéĴ±
    -0.08
    POSITIVE LOGITS
    jem
    0.10
    å±ĭ
    0.09
    achi
    0.09
    åħ¬çĽĬæ´»åĬ¨
    0.08
     pizza
    0.08
     Haram
    0.08
    åĨįä¹Łä¸į
    0.08
    éĩĮç¨ĭ
    0.08
    achu
    0.08
    èĤ¯
    0.08
    Activations Density 0.010%

    No Known Activations