© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52634
    Prev
    Next
    INDEX
    Explanations

    guest login

    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
    åŁ
    -0.10
    Ñīе
    -0.10
    åħļåĴĮåĽ½å®¶
    -0.10
    å´©
    -0.10
    çī¢è®°
    -0.09
    æ±Ĩ
    -0.09
    èĩªç§ģ
    -0.09
    åĿĤ
    -0.09
    æĶ¿æĿĥ
    -0.09
    .reporting
    -0.09
    POSITIVE LOGITS
    ICO
    0.09
    æľįåĬ¡äºİ
    0.08
    æıIJä¾Ľä¼ĺè´¨
    0.08
    edom
    0.08
    cast
    0.08
    ä¼ĺç§ĢçļĦ
    0.08
    æľĿéĺ³
    0.08
    7
    0.08
    als
    0.07
    ç¥ł
    0.07
    Activations Density 0.003%

    No Known Activations