© 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. 61699
    Prev
    Next
    INDEX
    Explanations

    phantom

    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
    ugu
    -0.09
    side
    -0.09
    bery
    -0.09
    ington
    -0.08
    onaut
    -0.08
     scrambling
    -0.08
    æķ´é¡¿
    -0.08
    ç¦Ĭ
    -0.08
    产ä¸ļåĮĸ
    -0.08
    ening
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.11
    omas
    0.10
    ry
    0.10
    ../../../
    0.10
    æ¹ĸåĮº
    0.09
    ental
    0.09
    IVEN
    0.09
    uras
    0.09
    astic
    0.09
    åľ¨èģĮ
    0.09
    Activations Density 0.003%

    No Known Activations