© 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. 34326
    Prev
    Next
    INDEX
    Explanations

    open source

    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
    ifax
    -0.09
    ä¹±
    -0.08
    ä¸ĸ纪
    -0.08
    驶
    -0.08
    éªĹ
    -0.08
    æĢķ
    -0.08
    èĤ¯
    -0.08
    èµİ
    -0.08
     century
    -0.08
     Guild
    -0.07
    POSITIVE LOGITS
    å¼ĢæºIJ
    0.11
    åħįè´¹
    0.11
    å¾Īä¸įéĶĻ
    0.10
    æ¡Ĩæŀ¶
    0.10
    åħ¬å¼Ģ
    0.10
     Grinder
    0.09
    волÑĮ
    0.09
    .sourceforge
    0.09
     developed
    0.09
    (open
    0.09
    Activations Density 0.640%

    No Known Activations