© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52559
    Prev
    Next
    INDEX
    Explanations

    terms or to negotiate

    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
    1
    -0.09
    天使
    -0.09
    0
    -0.09
    2
    -0.09
    åĩĢåĮĸ
    -0.08
    8
    -0.08
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.08
    9
    -0.08
    3
    -0.08
     outbound
    -0.08
    POSITIVE LOGITS
    æĹ©æĹ¥
    0.10
    å±ŀäºİèĩªå·±
    0.10
    หย
    0.10
    èİ·å¾ĹæĽ´å¤ļ
    0.10
    åħīæĺİ
    0.10
    å¤©çľŁ
    0.10
    VRT
    0.09
    ç¼ļ
    0.09
    为èĩªå·±
    0.09
    æį¢æĿ¥
    0.09
    Activations Density 0.099%

    No Known Activations