© 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. 9270
    Prev
    Next
    INDEX
    Explanations

    visible or handy location

    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
    endi
    -0.09
    ç³Ł
    -0.09
    人家
    -0.09
    åŀĵ
    -0.08
    зем
    -0.08
    èĤĸ
    -0.08
    engage
    -0.08
     Kensington
    -0.08
    为空
    -0.08
    åij
    -0.08
    POSITIVE LOGITS
    éĨĴ缮
    0.12
    åı¯è§ģ
    0.12
    æĺ¾
    0.11
    éļIJèĶ½
    0.11
     prominent
    0.11
    ä½įç½®
    0.10
    éĨĴ
    0.10
    端æŃ£
    0.10
    åݳ
    0.10
    ä¸ĩç¾İåħĥ
    0.10
    Activations Density 0.051%

    No Known Activations