© 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. 9464
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    使ä¹ĭ
    -0.09
    å½ĵä¹ĭ
    -0.09
    sel
    -0.09
    ä¹ĭæīĢ以
    -0.08
    æѤ
    -0.08
    .setProperty
    -0.08
    ä¸įä¿¡
    -0.08
     coordin
    -0.07
    æ¸ħåĩī
    -0.07
    åıijæĮ¥äºĨ
    -0.07
    POSITIVE LOGITS
    ä¸ĢåĪĩéĥ½æĺ¯
    0.10
    ä¾Ĩ說
    0.09
    说æĪij
    0.09
    è¿IJä½ľ
    0.09
    å±İ
    0.09
    æĿ¥è¯´
    0.09
    Accessory
    0.09
    åĿĮ
    0.08
    泯
    0.08
    å¤Ń
    0.08
    Activations Density 0.179%

    No Known Activations