© 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. 39514
    Prev
    Next
    INDEX
    Explanations

    high standard or level

    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
    _LD
    -0.09
    воÑĢ
    -0.09
     Affero
    -0.09
    _ld
    -0.09
    amic
    -0.09
    åµĺ
    -0.08
    åłĨ
    -0.08
    ishi
    -0.08
    (Abstract
    -0.08
    èIJĮ
    -0.08
    POSITIVE LOGITS
    æ°´åĩĨ
    0.19
    æ°´å¹³
    0.19
     level
    0.17
    level
    0.14
     ÑĥÑĢовенÑĮ
    0.14
    é«ĺæ°´å¹³
    0.14
    ãĥ¬ãĥĻãĥ«
    0.13
    (level
    0.13
    è¶Ĭé«ĺ
    0.13
    å¾Īé«ĺçļĦ
    0.13
    Activations Density 0.062%

    No Known Activations