© 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. 31693
    Prev
    Next
    INDEX
    Explanations

    something more

    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
    æľīç§į
    -0.11
    æľīåĩłä¸ª
    -0.09
    -li
    -0.09
    ä¸įç®¡ä½ł
    -0.09
    å½±éŁ³
    -0.09
    .Usage
    -0.09
    aghan
    -0.09
     ìŀĪì§Ģ
    -0.08
    mare
    -0.08
     ëħ
    -0.08
    POSITIVE LOGITS
    LER
    0.10
    çī¹åĪ«å£°æĺİ
    0.09
    éĿ¢è²Į
    0.09
    CLUSIVE
    0.09
    æĪijè¦ģ
    0.09
    æĪij们åı¯ä»¥
    0.09
    æĪij们è¦ģ
    0.09
    ç¹ģ
    0.08
    Listing
    0.08
    iedo
    0.08
    Activations Density 0.025%

    No Known Activations