© 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. 6973
    Prev
    Next
    INDEX
    Explanations

    grown to become

    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
    /vendors
    -0.10
    æĦı大
    -0.09
    çŁŃ
    -0.09
    ies
    -0.09
    çķ¿
    -0.09
    ä¸Ģ度
    -0.09
    nder
    -0.09
    æµĵ缩
    -0.09
    åıĺ为
    -0.08
    å·¥ä½ľç»ıéªĮ
    -0.08
    POSITIVE LOGITS
    owie
    0.10
    äºij端
    0.09
    æī¿æĭħ
    0.08
    æ¶īåıĬ
    0.08
    æ£Ĵ
    0.08
    æķijæ²»
    0.08
    ogie
    0.08
    [code
    0.08
    æĭĽ
    0.08
    ulia
    0.08
    Activations Density 0.019%

    No Known Activations