© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7229
    Prev
    Next
    INDEX
    Explanations

    app name and type

    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
    çļĵ
    -0.09
    åħ¢
    -0.09
     Sommer
    -0.08
     hob
    -0.08
    fra
    -0.08
    æľºåĻ¨
    -0.08
     technologies
    -0.08
    éĹ°
    -0.08
     Hunter
    -0.07
    Hunter
    -0.07
    POSITIVE LOGITS
    éļıæŶéļıåľ°
    0.12
    æİĮ
    0.10
    é«ĺæ¸ħ
    0.10
    èįĥ
    0.09
    çģµæĦŁ
    0.09
    èİ«æĸ¯
    0.09
    æĮĩå°ĸ
    0.09
     app
    0.09
    ä½Ľ
    0.09
    ç¢Ľ
    0.09
    Activations Density 0.560%

    No Known Activations