© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11735
    Prev
    Next
    INDEX
    Explanations

    frequency and degree

    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
    沸èħ¾
    -0.09
    çļĦä¸ĸçķĮ
    -0.09
    丼
    -0.09
    lemn
    -0.08
    说åĩº
    -0.08
    缸åºĶ
    -0.08
    tek
    -0.08
    indi
    -0.08
    ä¸Ģå®ļç¨ĭ度
    -0.08
     ÐłÐ¾Ñģ
    -0.08
    POSITIVE LOGITS
    avern
    0.09
    è®®äºĭ
    0.09
    åĮ£
    0.09
    æĻĤåĢĻ
    0.08
    opers
    0.08
    æŶåĢĻ
    0.08
    ackers
    0.08
    ponge
    0.08
    èĢģ人家
    0.08
     behalf
    0.08
    Activations Density 0.174%

    No Known Activations