© 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. 37564
    Prev
    Next
    INDEX
    Explanations

    SRC, GIG, sHSP, amino

    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
    _Dec
    -0.09
    æī§çĿĢ
    -0.08
    çŀ
    -0.08
    æĬŁ
    -0.08
    realm
    -0.08
    DECL
    -0.08
    æį§
    -0.08
     Anatomy
    -0.08
    ä¼Łå¤§çļĦ
    -0.08
    ç³ģ
    -0.08
    POSITIVE LOGITS
    DataGridViewTextBoxColumn
    0.11
    çĽijæĬ¤
    0.09
    å¸ĮæľĽå¤§å®¶
    0.09
    çķħ
    0.09
    å¤ĦåĪĨ
    0.08
    笳
    0.08
    æ¯ĶåĪĨ
    0.08
    积
    0.08
    jourd
    0.08
    çīĩåŃIJ
    0.08
    Activations Density 0.909%

    No Known Activations