© 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. 61709
    Prev
    Next
    INDEX
    Explanations

    wine and beverage names

    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
    agg
    -0.09
    çĥĻ
    -0.08
    æ·ĩ
    -0.08
     club
    -0.08
    åĽłåľ°
    -0.08
    åIJĮåŁİ
    -0.08
     montage
    -0.08
    PIO
    -0.08
     PIE
    -0.08
    çķħ
    -0.08
    POSITIVE LOGITS
    年产
    0.11
    çĶŁäº§çļĦ
    0.11
    åĩºäº§
    0.10
    产åĮº
    0.10
    ActionResult
    0.10
    失è°ĥ
    0.09
    å¢Ģ
    0.09
     Wass
    0.09
    è¿ĩå¾Ĺ
    0.09
    çłĸ
    0.09
    Activations Density 0.024%

    No Known Activations