© 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. 31870
    Prev
    Next
    INDEX
    Explanations

    allergic diseases and symptoms

    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
    å¿ĥæĦı
    -0.10
     Ñģобой
    -0.09
    OLE
    -0.09
    åıªè¦ģä½ł
    -0.09
    åĦ¿
    -0.09
    ational
    -0.08
     Elegant
    -0.08
     деÑıÑĤелÑĮноÑģÑĤÑĮ
    -0.08
    ä¸ģ
    -0.08
    ла
    -0.08
    POSITIVE LOGITS
    renc
    0.10
    erate
    0.09
    iances
    0.09
    اÙħر
    0.09
    沤
    0.09
    IFY
    0.08
    iras
    0.08
    avy
    0.08
    éĹ¾
    0.08
    icas
    0.08
    Activations Density 0.010%

    No Known Activations