© 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. 8776
    Prev
    Next
    INDEX
    Explanations

    perform as expected

    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
    åķIJ
    -0.09
    conds
    -0.09
     applic
    -0.09
    6
    -0.08
    çļĦæĦıä¹ī
    -0.08
    æ·ĭ
    -0.08
    ç©¿è¡£
    -0.08
    lic
    -0.08
    è¿ĻæĿ¡è·¯
    -0.08
    4
    -0.08
    POSITIVE LOGITS
    åĬŁèĥ½
    0.13
    è¿IJä½ľ
    0.10
     functionality
    0.09
    amon
    0.09
     function
    0.09
     funcion
    0.09
    大å®Ĺ
    0.09
    å«Į
    0.09
     functional
    0.09
     fonction
    0.09
    Activations Density 0.326%

    No Known Activations