© 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. 53194
    Prev
    Next
    INDEX
    Explanations

    website navigation

    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
    åı¦ä¸Ģä½į
    -0.10
    è¿Ļç§įäºĭæĥħ
    -0.09
    åıįä¹ĭ
    -0.08
     ‘
    -0.08
     âĢ
    -0.08
    èŀ³
    -0.07
    è°ģèĥ½
    -0.07
    太太
    -0.07
    èĩªçĦ¶èĢĮ
    -0.07
     http
    -0.07
    POSITIVE LOGITS
    OTH
    0.10
    agal
    0.09
    æ¸Ľ
    0.09
    ozo
    0.09
     Finch
    0.09
     Español
    0.09
    Donate
    0.09
    isky
    0.09
    寸
    0.09
    éĺģ
    0.08
    Activations Density 0.145%

    No Known Activations