© 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. 38127
    Prev
    Next
    INDEX
    Explanations

    cities in US states

    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
    ì¹ĺ
    -0.11
    encion
    -0.09
    _TC
    -0.08
    æľįåĬ¡æ°´å¹³
    -0.08
    æľįåĬ¡ä½ĵç³»
    -0.08
    iÄħ
    -0.08
    ÑģÑı
    -0.08
    驼
    -0.08
    读åIJİæĦŁ
    -0.08
    ÙĪØ·
    -0.08
    POSITIVE LOGITS
    à¹ģà¸Ľà¸¥
    0.09
    shire
    0.09
    ãĤ
    0.09
    ivos
    0.09
    vation
    0.08
    æįIJ
    0.08
    éľĸ
    0.08
    ner
    0.08
    çľĭä¸Ģä¸ĭ
    0.08
     Ngo
    0.08
    Activations Density 0.007%

    No Known Activations