© 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. 18181
    Prev
    Next
    INDEX
    Explanations

    celebrity names

    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
    追
    -0.10
    bedo
    -0.10
    æĪį
    -0.09
    交è°Ī
    -0.09
    壽
    -0.09
    occo
    -0.09
    elder
    -0.09
    æĮ¯åĬ¨
    -0.08
    jong
    -0.08
     Burke
    -0.08
    POSITIVE LOGITS
    ä¹ĭ乡
    0.09
    ç«ĸ
    0.09
    å¸ĿåĽ½
    0.08
    itti
    0.08
     Pist
    0.08
    èĨ¨
    0.08
     parad
    0.08
    è§ģè¯ģ
    0.08
     pil
    0.08
     Dor
    0.08
    Activations Density 0.004%

    No Known Activations