© 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. 48064
    Prev
    Next
    INDEX
    Explanations

    horse race and betting

    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
    çĶ·ç¯®
    -0.10
    岸
    -0.09
    pher
    -0.09
    篮çIJĥ
    -0.09
    æł¸ç®Ĺ
    -0.09
    æİĴæ¯Ĵ
    -0.09
    éĹ®åį·
    -0.09
    常åĬ¡åī¯
    -0.09
    ä¿®åħ»
    -0.09
    èī¦
    -0.08
    POSITIVE LOGITS
     race
    0.10
     Fut
    0.10
    串
    0.10
    akk
    0.09
    é¬ĥ
    0.09
    race
    0.09
     rac
    0.09
     racing
    0.08
     Races
    0.08
    èĶ½
    0.08
    Activations Density 0.073%

    No Known Activations