© 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. 5823
    Prev
    Next
    INDEX
    Explanations

    is problem or answer

    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
    å¿ħçĦ¶
    -0.10
    å°±å¾Ĺ
    -0.10
    ãģłãģijãģ§ãģªãģı
    -0.09
    çļĦ好å¤Ħ
    -0.08
    纯
    -0.08
    usi
    -0.08
    bid
    -0.08
    ä¸įæŃ¢
    -0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    ани
    -0.08
    POSITIVE LOGITS
    åĢĴæĺ¯
    0.16
    è¿Ļæīįæĺ¯
    0.14
    æīįæĺ¯
    0.14
    æīįæĺ¯çľŁæŃ£
    0.13
    æĽ´å¤ļçļĦæĺ¯
    0.10
    羣æŃ£
    0.10
    åıįåĢĴ
    0.10
    æĮ¤
    0.10
    缸æ¯Ķä¹ĭä¸ĭ
    0.09
    åıįèĢĮ
    0.09
    Activations Density 0.067%

    No Known Activations