© 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. 38840
    Prev
    Next
    INDEX
    Explanations

    nature and natural descriptions

    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
    ä¸Ģ个个
    -0.11
    abled
    -0.10
    oden
    -0.10
    nuts
    -0.09
    æĤłæĤł
    -0.09
    openh
    -0.09
    æī§æĦı
    -0.08
    ht
    -0.08
    ieg
    -0.08
    нÑıÑĤ
    -0.08
    POSITIVE LOGITS
    æģ¯
    0.10
    riter
    0.09
    å·¨
    0.09
    educ
    0.08
    ç®ķ
    0.08
     гол
    0.08
    çķĮçļĦ
    0.08
    èĩªçĦ¶
    0.08
    tic
    0.08
    cation
    0.08
    Activations Density 0.010%

    No Known Activations