© 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. 37594
    Prev
    Next
    INDEX
    Explanations

    .gl/ links

    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
    åѤåįķ
    -0.09
    滥
    -0.09
    社ä¼ļç»Ħç»ĩ
    -0.09
     hẹ
    -0.09
     гол
    -0.09
    åıijå±ķçIJĨ念
    -0.09
    å¼ģ
    -0.08
    Orm
    -0.08
    rom
    -0.08
    åıijå±ķæĸ¹åIJij
    -0.08
    POSITIVE LOGITS
    ãĥķãĥªãĥ¼
    0.10
    imony
    0.10
    è¯
    0.08
    好äºĨ
    0.08
    è¯Ľ
    0.08
    .future
    0.08
    æľ¬èº«
    0.08
    å¤ıåŃ£
    0.08
    ointed
    0.08
    IJèĹı
    0.08
    Activations Density 0.004%

    No Known Activations