© 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. 21241
    Prev
    Next
    INDEX
    Explanations

    legislature and assembly

    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
    糧
    -0.10
     Hind
    -0.09
    æĬijéĥģ
    -0.08
     tuyá»ĩt
    -0.08
    ua
    -0.08
    æݥ管
    -0.08
    å½ĵä¹ĭ
    -0.08
    ora
    -0.08
    ish
    -0.07
    stead
    -0.07
    POSITIVE LOGITS
    inded
    0.10
    ÑĪин
    0.09
    аÑĢам
    0.09
    ffen
    0.09
    ences
    0.09
    èģª
    0.09
     ÑģÑĤÑĢанÑĭ
    0.08
    èĪ«
    0.08
    lexport
    0.08
    èįīæ¡Ī
    0.08
    Activations Density 0.014%

    No Known Activations