© 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. 48508
    Prev
    Next
    INDEX
    Explanations

    new and

    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
    agi
    -0.11
    kap
    -0.10
    å½ĵãģŁãĤĬ
    -0.09
    å¤ļåľ°
    -0.09
    оÑĩно
    -0.09
    è·¨
    -0.09
    .pb
    -0.09
    æĵį
    -0.08
    å§Ĺ
    -0.08
    âģ»
    -0.08
    POSITIVE LOGITS
    /new
    0.09
     Zealand
    0.09
    /New
    0.09
    æŃ£çīĪ
    0.09
    ä¸ĢæľŁ
    0.09
    è£Ĵ
    0.08
    ä¸ĸçķĮ第ä¸Ģ
    0.08
    溷
    0.08
    æĮ½
    0.08
    æİĩ
    0.08
    Activations Density 0.021%

    No Known Activations