© 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. 23418
    Prev
    Next
    INDEX
    Explanations

    Swifty McVay, Tighty-whiteys

    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
    inea
    -0.10
    IRM
    -0.09
    inus
    -0.09
    imming
    -0.09
     ÑĢÑĭ
    -0.08
    _hosts
    -0.08
    _TUN
    -0.08
    åĩĢæ°´
    -0.08
    岫
    -0.08
    åĶı
    -0.08
    POSITIVE LOGITS
    ies
    0.10
    lic
    0.10
    åıijæĮ¥
    0.09
    è¾¹éĻħ
    0.09
    camp
    0.09
    ä¸įç¡®å®ļæĢ§
    0.09
    é¥Ńèıľ
    0.08
    æ¸Į
    0.08
    主åĬ¨æĢ§
    0.08
    éĨ´
    0.08
    Activations Density 0.146%

    No Known Activations