© 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. 27670
    Prev
    Next
    INDEX
    Explanations

    predicament, reminding, likes, wants, born

    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
    ä¸ŃéĹ´
    -0.09
    æ¢Ĺ
    -0.08
    æĦŁæħ¨
    -0.08
    éľ²
    -0.08
    Lik
    -0.08
    idy
    -0.08
    ëĬIJ
    -0.08
     Chung
    -0.07
    ovy
    -0.07
    à¹ĭ
    -0.07
    POSITIVE LOGITS
    æĪijä¸įæĥ³
    0.10
    ä¿©
    0.10
    пиÑģаÑĤÑĮ
    0.09
    ÑĥÑĩа
    0.09
    unan
    0.09
    绿水éĿĴå±±
    0.09
    å³Ļ
    0.09
    æīĢ以æĪij
    0.09
    æŁŀ
    0.09
    åĢij
    0.09
    Activations Density 0.072%

    No Known Activations