© 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. 49659
    Prev
    Next
    INDEX
    Explanations

    while in

    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
    гÑĢани
    -0.09
    绾
    -0.09
    ales
    -0.09
    æĺ¯éĿŀ
    -0.09
    æĭĶ
    -0.09
    ulton
    -0.09
    æī§çĿĢ
    -0.08
    ä¸ĩäºĭ
    -0.08
    _Pl
    -0.08
    ä»Ģ
    -0.08
    POSITIVE LOGITS
    oven
    0.10
     Nug
    0.09
    çĽ¥
    0.09
    æıŃéľ²
    0.09
    女æľĭåıĭ
    0.08
    åIJĪä½ľåħ³ç³»
    0.08
    oz
    0.08
    çĶŁçĹħ
    0.08
    iard
    0.08
    æĸ°åĨłèĤºçĤİ
    0.08
    Activations Density 0.036%

    No Known Activations