© 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. 18206
    Prev
    Next
    INDEX
    Explanations

    author or artist

    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
     itself
    -0.10
    æīĵçĮİ
    -0.09
     каз
    -0.08
    ething
    -0.08
    actors
    -0.08
    å®ĥ
    -0.08
    æľ¬èº«
    -0.08
    æīĢåľ¨åľ°
    -0.08
    éĢļ
    -0.08
    ä¿Ŀéļľ
    -0.08
    POSITIVE LOGITS
    æĺ¯è°ģ
    0.12
     prolific
    0.11
    çļĦä½ľåĵģ
    0.11
    åIJįæ°Ķ
    0.11
    ä½ľåĵģ
    0.11
    é£İæł¼
    0.11
     whose
    0.11
    whose
    0.10
    æĵħéķ¿
    0.10
    çĹĶ
    0.10
    Activations Density 0.147%

    No Known Activations