© 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. 56913
    Prev
    Next
    INDEX
    Explanations

    Copyright notices and licenses

    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
    ä»ĸçļĦ
    -0.10
    ityEngine
    -0.10
    åľ¨ä»Ĭå¹´
    -0.09
    sPid
    -0.09
    赶
    -0.09
    erk
    -0.09
    mPid
    -0.09
     جدا
    -0.09
    âĹ»
    -0.09
    ORY
    -0.09
    POSITIVE LOGITS
    /or
    0.11
    empre
    0.09
    atra
    0.08
    éĴ®
    0.08
    -or
    0.08
    up
    0.08
     sẵ
    0.08
    aus
    0.08
     reap
    0.07
    åĨįçİ°
    0.07
    Activations Density 1.952%

    No Known Activations