© 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. 56992
    Prev
    Next
    INDEX
    Explanations

    family and friends

    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
    ä¸ĢåĪĩéĥ½
    -0.09
    åĬĽåѦ
    -0.08
     LIVE
    -0.08
    ksi
    -0.08
    以æѤ
    -0.08
     каÑĩеÑģÑĤво
    -0.08
    Concrete
    -0.08
    èµłéĢģ
    -0.08
     mechanic
    -0.08
    .origin
    -0.08
    POSITIVE LOGITS
    ä¸Ģæł·çļĦ
    0.09
    gone
    0.09
    åĩºè·¯
    0.09
    ä¸įå¿į
    0.09
    æĺ¯æĪij们
    0.09
    亲åĪĩ
    0.09
    æĪij们认为
    0.09
    å¸Ĥåľºä¸»ä½ĵ
    0.09
    ç»ĻæĪij们
    0.09
    ä»ĩ
    0.09
    Activations Density 0.032%

    No Known Activations