© 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. 17141
    Prev
    Next
    INDEX
    Explanations

    memorandum opinion

    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
    ivo
    -0.09
    iable
    -0.09
    度
    -0.09
    ÃŃvel
    -0.08
    eldo
    -0.08
    æ¸Ĭ
    -0.08
    å´ĩ
    -0.08
     Concurrent
    -0.07
    ibaba
    -0.07
    criptors
    -0.07
    POSITIVE LOGITS
     thuế
    0.10
    stry
    0.10
    沿海
    0.10
     memo
    0.10
    memo
    0.10
    áĢı
    0.10
    ìĤ¬íķŃ
    0.10
    åĵ¡
    0.09
    ÙĪض
    0.09
    åijĺ
    0.09
    Activations Density 0.012%

    No Known Activations