© 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. 52206
    Prev
    Next
    INDEX
    Explanations

    US state abbreviations

    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
    burger
    -0.09
    æµ·åĨħå¤ĸ
    -0.09
    åĽ½éĻħå¸Ĥåľº
    -0.09
    æī¼
    -0.08
    _DIGEST
    -0.08
     оÑĢганизм
    -0.08
    çĸĶ
    -0.08
    å¾Ĺ罪
    -0.08
    째
    -0.08
    chl
    -0.08
    POSITIVE LOGITS
    æĸ¹åľĨ
    0.09
    综
    0.08
     Nacht
    0.08
    onne
    0.08
    çī¹äº§
    0.08
    çĶŁäº§å·¥èīº
    0.08
    tractor
    0.08
    åºł
    0.08
     Gün
    0.08
    LECTION
    0.07
    Activations Density 0.049%

    No Known Activations