© 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. 35732
    Prev
    Next
    INDEX
    Explanations

    some followed by a noun or adjective

    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
    ä¸Ģ声
    -0.12
     somewhat
    -0.10
    most
    -0.10
    ä¸Ģå¹ķ
    -0.10
    ä¸Ģåľº
    -0.10
    de
    -0.10
    ä¸Ģç§į
    -0.10
    è¿Ļç§įæĥħåĨµ
    -0.10
    åħ¶ä¸Ńä¸Ģ个
    -0.10
    大éĥ¨åĪĨ
    -0.10
    POSITIVE LOGITS
    /all
    0.21
    place
    0.17
    æŶåĢĻ
    0.14
    æĻĤåĢĻ
    0.14
    ones
    0.14
    çĶļèĩ³æĺ¯
    0.12
    -times
    0.12
    pon
    0.12
    hw
    0.11
    brero
    0.11
    Activations Density 0.118%

    No Known Activations