© 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. 62017
    Prev
    Next
    INDEX
    Explanations

    industry

    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
    å°¼äºļ
    -0.11
    ró
    -0.11
    产ä¸ļåĽŃåĮº
    -0.09
    å°Ķæĸ¯
    -0.09
    ness
    -0.09
    tern
    -0.09
    æł·çļĦ
    -0.09
     dạ
    -0.09
    èĦijè¢ĭ
    -0.09
    itude
    -0.08
    POSITIVE LOGITS
    wide
    0.14
    -wide
    0.12
    -standard
    0.11
    人士
    0.10
    åĨħçļĦ
    0.09
    -leading
    0.09
    çĬ¶åĨµ
    0.09
    ally
    0.09
    sek
    0.09
    ä¸ŃæľĢ
    0.09
    Activations Density 0.023%

    No Known Activations