© 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. 22993
    Prev
    Next
    INDEX
    Explanations

    ranked, losses, points, or records

    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
    åıĭæĥħ
    -0.10
    воз
    -0.09
    _CAT
    -0.09
    CharacterSet
    -0.09
    åĨĻåĩº
    -0.09
    ç»ĥä¹ł
    -0.09
    ternal
    -0.09
    enery
    -0.09
     ÑģÑĤоÑĢ
    -0.09
    çķħ
    -0.09
    POSITIVE LOGITS
    ä»ħ次äºİ
    0.12
    åħ¶ä¸Ńæľī
    0.09
    åħ¶ä¸ŃåĮħæĭ¬
    0.09
    æľįä»İ
    0.09
    æľĢå¤ļçļĦ
    0.08
    迹
    0.08
    åİĨåı²æĸ°é«ĺ
    0.08
    ansen
    0.08
    ppt
    0.08
    AML
    0.08
    Activations Density 0.027%

    No Known Activations