© 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. 2536
    Prev
    Next
    INDEX
    Explanations

    new blank

    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
    illow
    -0.09
    è¡®
    -0.08
    åħĦå¼Ł
    -0.08
    åĵ¥
    -0.08
    å¾®åįļ
    -0.08
    æİĪæĿĥ
    -0.08
     downside
    -0.08
     ordering
    -0.08
    åĩıéĢŁ
    -0.08
    _NEG
    -0.08
    POSITIVE LOGITS
    äºļ马
    0.09
    æ¬Ħ
    0.09
    èĸª
    0.09
    åĵ¨
    0.08
    -alt
    0.08
     Shortcut
    0.08
    äººæł¼
    0.08
    Salvar
    0.08
    éļIJèĹı
    0.08
    äºĴéĢļ
    0.08
    Activations Density 0.171%

    No Known Activations