© 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. 57356
    Prev
    Next
    INDEX
    Explanations

    computers

    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
    é«ĺæłĩåĩĨ
    -0.09
     HMAC
    -0.09
    æĸĩæ¡Ī
    -0.08
    ç½
    -0.08
    移æ¤į
    -0.08
    ê¶Į
    -0.08
    .API
    -0.08
    æĪ¿ä¼ģ
    -0.08
    ç¼ī
    -0.08
    erek
    -0.08
    POSITIVE LOGITS
    计ç®Ĺæľº
    0.19
     computer
    0.17
     компÑĮÑİÑĤеÑĢ
    0.16
     ì»´íĵ¨íĦ°
    0.15
    çĶµèĦij
    0.15
    computer
    0.15
     computers
    0.15
    Computer
    0.14
     Computer
    0.14
     COMPUTER
    0.13
    Activations Density 0.136%

    No Known Activations