© 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. 4034
    Prev
    Next
    INDEX
    Explanations

    time followed by specific words

    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
    åĬłå·¥
    -0.10
    åºķæ°Ķ
    -0.10
    пеÑĩаÑĤ
    -0.10
     troch
    -0.09
    æ·±åĬłå·¥
    -0.09
    avan
    -0.09
    åĵªæĢķæĺ¯
    -0.09
    getResult
    -0.09
    ï½¼
    -0.08
    atie
    -0.08
    POSITIVE LOGITS
    裸
    0.09
    èĥ¶åĽĬ
    0.08
    绯
    0.08
    èĩ³æѤ
    0.08
     Rochester
    0.08
    boxed
    0.08
    OfDay
    0.08
     rot
    0.08
    éĢ¢
    0.07
    æī¼
    0.07
    Activations Density 0.045%

    No Known Activations