© 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. 56560
    Prev
    Next
    INDEX
    Explanations

    license identifiers

    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
    路桥
    -0.10
    unde
    -0.08
    åŃ¦ä¹łæĪIJ绩
    -0.08
    ä¸įéĹ´æĸŃ
    -0.08
    undos
    -0.08
     Booker
    -0.08
    unce
    -0.08
    æģĤ
    -0.08
     ÐłÐ¾
    -0.08
     frau
    -0.08
    POSITIVE LOGITS
    AGES
    0.09
    iates
    0.09
    avia
    0.09
    èĥ½å¾ĹåĪ°
    0.09
    ewise
    0.09
    kö
    0.08
    ottom
    0.08
    cls
    0.08
    iva
    0.08
    åĴĮåıijå±ķ
    0.08
    Activations Density 0.452%

    No Known Activations