© 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. 5018
    Prev
    Next
    INDEX
    Explanations

    install or trial

    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
    éħįå¥Ĺ设æĸ½
    -0.09
    ä¾ĽåºĶ
    -0.09
    _DIP
    -0.08
    è¹Ģ
    -0.08
    /swagger
    -0.08
    çĪ±å¥½
    -0.08
    äºĮæīĭ
    -0.08
    åĬłå¿«æİ¨è¿Ľ
    -0.08
    åŃĹ
    -0.08
    èĨĿçĽĸ
    -0.08
    POSITIVE LOGITS
    åħ¨å®¶
    0.11
    æĹĹèĪ°
    0.11
    峡
    0.10
    åĵ¨
    0.09
    åħ¨éĿ¢æıIJåįĩ
    0.09
    Aware
    0.09
    é©»
    0.09
    妻
    0.09
    åħ¨éĿ¢
    0.09
    ä¸ĢéĿ¢
    0.09
    Activations Density 0.088%

    No Known Activations