© 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. 1508
    Prev
    Next
    INDEX
    Explanations

    ever increasing

    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¨ļ
    -0.09
    ä¸Ģæł·çļĦ
    -0.08
    utto
    -0.08
    äºĨå¾Īä¹ħ
    -0.08
    çī¹è´¨
    -0.08
    æŶä¸į
    -0.08
    dojo
    -0.08
     Laur
    -0.08
    沿线
    -0.08
    çī¹æ®ĬçļĦ
    -0.08
    POSITIVE LOGITS
    ennen
    0.10
    ingly
    0.09
    继
    0.09
    åħīèį£
    0.09
    enticator
    0.09
     пÑĢакÑĤиÑĩеÑģки
    0.08
    IMER
    0.08
     Sunny
    0.08
    eil
    0.08
    ä»ĸ对
    0.08
    Activations Density 0.016%

    No Known Activations