© 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. 56435
    Prev
    Next
    INDEX
    Explanations

    uilleann pipes

    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¸Ńéĵģ
    -0.10
    edly
    -0.10
    åŀĤ
    -0.09
    åĨķ
    -0.09
    æĴŃ
    -0.09
    _codegen
    -0.09
    è±ĨæµĨ
    -0.09
    edList
    -0.09
    踵
    -0.09
    ä¸įç¦ģ
    -0.09
    POSITIVE LOGITS
    大æĸ¹
    0.08
    ilers
    0.08
    æIJĤ
    0.08
    hort
    0.08
    磫
    0.08
    ential
    0.08
    ä½Ĩ她
    0.08
    äºĭåĦ¿
    0.08
    ork
    0.08
     Dah
    0.08
    Activations Density 0.008%

    No Known Activations