© 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. 38502
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    欤
    -0.09
    äºĮåŃĹ
    -0.09
    earn
    -0.09
    .exe
    -0.08
    è¿Ļæł·ä¸Ģ个
    -0.08
    约
    -0.08
    é¢ģåıij
    -0.08
    æ½ľ
    -0.08
    æł¸å®ŀ
    -0.08
    ================================================================================
    -0.08
    POSITIVE LOGITS
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.12
    ì§ľ
    0.10
    å·¦åı³
    0.09
    åİ»äºĨ
    0.09
     namedtuple
    0.09
    cheid
    0.09
    ograms
    0.09
    èĤłèĥĥ
    0.08
    èī¯
    0.08
    uum
    0.08
    Activations Density 0.124%

    No Known Activations