© 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. 7695
    Prev
    Next
    INDEX
    Explanations

    from now on

    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
    åħ³éŨ
    -0.09
    ä¸įèĩ³äºİ
    -0.09
    ä»įæľª
    -0.09
    æĢİä¹Īä¼ļ
    -0.09
    æĢ»ä½ĵè§ĦåĪĴ
    -0.09
    çģ«çĤ¬
    -0.09
    aires
    -0.09
    linger
    -0.09
    åħĪåIJİ
    -0.09
    æıIJ示
    -0.09
    POSITIVE LOGITS
    ä»İæѤ
    0.16
    èĩªæѤ
    0.14
    åĨįä¹Łä¸į
    0.13
    æѤåIJİ
    0.12
    ä»ĬåIJİ
    0.12
    以åIJİ
    0.12
    以å¾Į
    0.11
    åĨįä¹Łæ²¡æľī
    0.11
    ä¸įè¦ģåĨį
    0.11
    åĨįä¹Ł
    0.11
    Activations Density 0.057%

    No Known Activations