© 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. 51337
    Prev
    Next
    INDEX
    Explanations

    dimensions or measurements

    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
    éľĨ
    -0.08
    éħŀ
    -0.08
    棱
    -0.08
    ä½ĵè´¨
    -0.08
    ntl
    -0.08
    å¾Ī好
    -0.08
    ozilla
    -0.08
    éĢIJ
    -0.08
    Scalar
    -0.08
    fäll
    -0.07
    POSITIVE LOGITS
    ä¹ĥèĩ³
    0.11
    -sized
    0.11
     sized
    0.10
    ä¸Ģ带
    0.10
    /ng
    0.10
    çļĦåľ°æŃ¥
    0.09
    èĮĥåĽ´åĨħ
    0.09
    诬
    0.09
    åıĬ以ä¸Ĭ
    0.09
    æ°´å¹³
    0.09
    Activations Density 0.069%

    No Known Activations