© 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. 36119
    Prev
    Next
    INDEX
    Explanations

    then followed by verbs

    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
    æѤæŶ
    -0.10
    ERA
    -0.09
    æ¯ıä¸Ģ次
    -0.09
    era
    -0.09
    å½ĵæŶ
    -0.09
    æĽ©
    -0.09
    èµ·åĪĿ
    -0.09
    è¿ĻæŶåĢĻ
    -0.09
    è¿ĻæŶ
    -0.09
    åIJ¦åĪĻ
    -0.09
    POSITIVE LOGITS
    lund
    0.09
    éĻħ
    0.09
    _track
    0.08
    çļİ
    0.08
    èµĸ以
    0.08
    Ve
    0.08
    ãģĿãĤĮãĤĴ
    0.08
    åģ¥
    0.08
    åĮĸå·¥
    0.08
    hir
    0.07
    Activations Density 0.050%

    No Known Activations