© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37170
    Prev
    Next
    INDEX
    Explanations

    sports game outcomes

    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
    æĥ³åĬŀæ³ķ
    -0.10
    ego
    -0.09
    积æŀģæİ¨è¿Ľ
    -0.09
    çĶµåŃIJä¿¡æģ¯
    -0.09
    æĪ·
    -0.09
    agem
    -0.09
    å½ķéŁ³
    -0.08
    éĵ¢
    -0.08
    è¹ij
    -0.08
    veau
    -0.08
    POSITIVE LOGITS
     Jaw
    0.10
    enas
    0.10
     jaw
    0.09
    çĭ¬
    0.09
    VERR
    0.09
    åħ¸ç¤¼
    0.09
    .sender
    0.08
    éĺŁåijĺ们
    0.08
    fst
    0.08
     Fla
    0.08
    Activations Density 0.003%

    No Known Activations