© 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. 29847
    Prev
    Next
    INDEX
    Explanations

    html table elements

    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
    饮
    -0.09
    é½
    -0.09
    è¶Ķ
    -0.09
    æĤĴ
    -0.09
    åı¯æĥ³èĢĮçŁ¥
    -0.09
    æł·çļĦ
    -0.08
    没æľīæĥ³åĪ°
    -0.08
    woods
    -0.08
    iked
    -0.08
    éĹ®ä»ĸ
    -0.08
    POSITIVE LOGITS
    æ¯Ĵ
    0.09
    ateg
    0.09
    èī¯æĢ§
    0.09
    oli
    0.08
     zen
    0.08
     Kum
    0.08
    åĪĪ
    0.08
    åıijè¨Ģ
    0.08
    åıĤ
    0.08
    Extern
    0.08
    Activations Density 0.294%

    No Known Activations