© 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. 34711
    Prev
    Next
    INDEX
    Explanations

    web server MVC edition

    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
    ç¿»
    -0.08
    dig
    -0.08
    resenter
    -0.07
    ä¸ĵ
    -0.07
    èµį
    -0.07
    rale
    -0.07
     lj
    -0.07
    å°ķ
    -0.07
     Will
    -0.07
     Wo
    -0.07
    POSITIVE LOGITS
    çļĤ
    0.10
    èĩªçĶ±è´¸æĺĵ
    0.10
    éŃģ
    0.10
     ìłľíĴĪ
    0.10
    产åĵģçłĶåıij
    0.10
    产åĵģ
    0.10
     DevExpress
    0.09
     yazılı
    0.09
    强壮
    0.09
    æł¸å¿ĥæĬĢæľ¯
    0.09
    Activations Density 0.181%

    No Known Activations