© 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. 7014
    Prev
    Next
    INDEX
    Explanations

    numbers indicating quantity or score

    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
    çĭ¬æľīçļĦ
    -0.10
    å¥ĩå¦Ļ
    -0.10
    踹
    -0.10
    çĿĩ
    -0.09
    nty
    -0.09
    fel
    -0.09
    ButtonItem
    -0.09
    åĶ¯
    -0.08
    æ´İ
    -0.08
    个åĪ«
    -0.08
    POSITIVE LOGITS
    InChildren
    0.08
    ConnectionFactory
    0.08
    aben
    0.08
    åľ¨æľªæĿ¥
    0.08
    ollow
    0.08
    åľ¨å¸Ĥåľºä¸Ĭ
    0.07
    çŃīæĸ¹å¼ı
    0.07
    æ³·
    0.07
    æ²Ľ
    0.07
    çĽ¸ä¿¡å¤§å®¶
    0.07
    Activations Density 0.002%

    No Known Activations