© 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. 11530
    Prev
    Next
    INDEX
    Explanations

    restrict, limit, access, scope

    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
    ä¹ŁçŁ¥éģĵ
    -0.10
    å¾Īæ¸ħæ¥ļ
    -0.09
    ä¹°åįķ
    -0.09
    樯
    -0.09
    身亡
    -0.09
    ä¸įéĹ´æĸŃ
    -0.09
    æĥħ人èĬĤ
    -0.09
    å¿ĺè®°
    -0.09
    è¡ĹåĮº
    -0.09
    æŃ£ä¹ī
    -0.09
    POSITIVE LOGITS
     scope
    0.12
    ä¸įåĩĨ
    0.10
    åıªèĥ½
    0.10
    å±ĢéĻIJäºİ
    0.10
     access
    0.10
    次æķ°
    0.10
    scope
    0.10
     restricted
    0.09
    èĩªçĶ±
    0.09
     limited
    0.09
    Activations Density 0.114%

    No Known Activations