© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37118
    Prev
    Next
    INDEX
    Explanations

    configuration keys

    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
    å®ĥåı¯ä»¥
    -0.09
    {}.
    -0.08
    _indicator
    -0.08
     gv
    -0.08
    éĢīæĭ
    -0.08
     hypert
    -0.08
    两级
    -0.08
    and
    -0.08
    人家
    -0.08
    æķijåij½
    -0.08
    POSITIVE LOGITS
    åIJįåı«
    0.10
    为ä½ķ
    0.10
    (crate
    0.10
    åĶ®ä»·
    0.10
    .isArray
    0.09
    æĪ¾
    0.09
    éĴĵ
    0.09
    èĤĥ
    0.09
    å±ĭéĩĮ
    0.09
    ä½ĵéĩį
    0.09
    Activations Density 1.110%

    No Known Activations