© 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. 4194
    Prev
    Next
    INDEX
    Explanations

    difference in

    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
    çłĴ
    -0.09
    asti
    -0.09
     turtles
    -0.09
    gether
    -0.09
    éĽĢ
    -0.09
    äºĶæĺŁ
    -0.09
    æµĭè¯Ħ
    -0.09
     indis
    -0.08
    èµĸ以
    -0.08
    quisites
    -0.08
    POSITIVE LOGITS
    对å¾ħ
    0.15
     between
    0.13
     междÑĥ
    0.11
    between
    0.11
    iating
    0.11
    iates
    0.11
     miÄĻdzy
    0.11
    _between
    0.10
    åįĹåĮĹ
    0.10
    ä¹ĭéĹ´çļĦ
    0.10
    Activations Density 0.140%

    No Known Activations