© 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. 55847
    Prev
    Next
    INDEX
    Explanations

    installing software or packages

    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
    åıªè¦ģä½ł
    -0.10
    èĭ¥æĤ¨
    -0.10
    å°Ķæĸ¯
    -0.10
    æĹłæķĮ
    -0.10
    æĬĬä½ł
    -0.10
    ä½łçİ°åľ¨
    -0.10
    å¸®ä½ł
    -0.10
    éĿ¢æĿ¡
    -0.09
    NIC
    -0.09
    å±ĬæŶ
    -0.09
    POSITIVE LOGITS
    ä¼¼ä¹İ
    0.09
     seems
    0.08
    7
    0.08
    6
    0.08
    æŁı
    0.08
    ä½Ĩæĺ¯æĪij
    0.08
    è¿Ľè¡ĮäºĨ
    0.08
    ä¹ŁæĹłæ³ķ
    0.08
    ToDevice
    0.08
     supposedly
    0.08
    Activations Density 4.555%

    No Known Activations