© 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. 1397
    Prev
    Next
    INDEX
    Explanations

    a single portion

    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
    -way
    -0.09
    ponent
    -0.09
    į°
    -0.09
    åij³éģĵ
    -0.09
    æľĽ
    -0.09
    æŀģ
    -0.09
    ducted
    -0.09
    æģŃ
    -0.08
    ä»ĭ
    -0.08
     Gust
    -0.08
    POSITIVE LOGITS
     íķĺëĤĺ
    0.10
     одной
    0.10
     одного
    0.09
    æīĢåľ¨
    0.09
    è´¶
    0.09
    å°ijæķ°
    0.09
    æľīæŶåĢĻ
    0.08
     одним
    0.08
    ä¹ĭä¸Ģ
    0.08
     one
    0.08
    Activations Density 0.148%

    No Known Activations