© 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. 29791
    Prev
    Next
    INDEX
    Explanations

    whitehaven resigns

    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
    ä¹İ
    -0.11
    大海
    -0.10
    å³Ļ
    -0.09
    à¹īà¸Ńม
    -0.09
    ä¼Łå¤§
    -0.09
    åĿĢ
    -0.09
    海峡
    -0.08
    orama
    -0.08
    ndef
    -0.08
    æ°ijçĶ¨
    -0.08
    POSITIVE LOGITS
    å¾Ģä¸Ĭ
    0.09
    ä¸Ģå°ģ
    0.08
    Ñĩин
    0.08
    æĸ¹åľĨ
    0.08
    é¦ĸ次
    0.08
    ç¿©
    0.08
    ç¼ł
    0.07
    æ±Ĺ
    0.07
    åĨĹ
    0.07
    è½»
    0.07
    Activations Density 0.002%

    No Known Activations