© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9540
    Prev
    Next
    INDEX
    Explanations

    days/weeks/months ago/before/later

    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
    ofs
    -0.10
    äºĨ大éĩıçļĦ
    -0.09
    çģ«çĥ§
    -0.09
    äºĨ许å¤ļ
    -0.09
    éŃħåĬĽ
    -0.09
    azor
    -0.09
    åįĬ个
    -0.09
    _MATH
    -0.08
    满满
    -0.08
    åħ¶æīĢ
    -0.08
    POSITIVE LOGITS
    ä¹ĥèĩ³
    0.10
     dozen
    0.10
    ager
    0.10
    reed
    0.09
    çĶļèĩ³æĺ¯
    0.09
    æĢ»ä¹ĭ
    0.08
    èĭĵ
    0.08
    (:,:,
    0.08
    iken
    0.08
    MUX
    0.08
    Activations Density 0.042%

    No Known Activations