© 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. 19783
    Prev
    Next
    INDEX
    Explanations

    contributor license

    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
    -0.11
    ifier
    -0.10
    ification
    -0.10
    éĹ¼
    -0.10
     ден
    -0.09
    uality
    -0.09
    ä¸ĵ人
    -0.09
    ä¿ļ
    -0.09
    éĹ¾
    -0.09
    yna
    -0.09
    POSITIVE LOGITS
    ary
    0.10
    itional
    0.10
    ivism
    0.09
    iting
    0.09
    ãģ¡ãģ¯
    0.09
    룬
    0.09
    ı
    0.09
    hip
    0.09
    APTER
    0.09
    £
    0.09
    Activations Density 0.027%

    No Known Activations