© 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. 36899
    Prev
    Next
    INDEX
    Explanations

    license version

    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
    éĹ´éļĶ
    -0.09
    éħ¸
    -0.08
     Heller
    -0.08
    è·µ
    -0.08
     Sey
    -0.08
    amental
    -0.08
     Dillon
    -0.08
    èĭ·
    -0.08
    unik
    -0.08
    InThe
    -0.08
    POSITIVE LOGITS
    abad
    0.09
    èįĥ
    0.09
    ect
    0.09
    æIJºæīĭ
    0.09
    åħļé£İ
    0.08
    æĬķè¯ī
    0.08
    ç°ĩ
    0.08
    çĽ
    0.08
    éħįæĸ¹
    0.08
    зд
    0.08
    Activations Density 0.044%

    No Known Activations