© 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. 19170
    Prev
    Next
    INDEX
    Explanations

    open source

    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
    滥çĶ¨
    -0.11
    好æľĭåıĭ
    -0.10
    è§ģæķĪ
    -0.09
    ä¹°æĪ¿
    -0.09
    å¿ĥ头
    -0.09
    åīįæīĢ
    -0.09
    çļĦåķĨåĵģ
    -0.09
    溢价
    -0.08
    çŁ¿æ³īæ°´
    -0.08
    ocalypse
    -0.08
    POSITIVE LOGITS
    -minded
    0.09
    éļ¾æĢª
    0.09
     architecture
    0.08
    鸳
    0.08
    åħij
    0.08
     provinc
    0.08
     equ
    0.08
    liness
    0.08
    _closure
    0.08
    ady
    0.08
    Activations Density 0.028%

    No Known Activations