© 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. 32922
    Prev
    Next
    INDEX
    Explanations

    list or array indexing

    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
    gid
    -0.09
    rolls
    -0.09
    æ´ĹèĦ¸
    -0.08
    ROLL
    -0.08
    ä¸įèĩ³äºİ
    -0.08
    åĴ¤
    -0.08
    é£Ļ
    -0.07
    /testing
    -0.07
    ä¸įå®ļ
    -0.07
    ably
    -0.07
    POSITIVE LOGITS
    èĦ±èIJ½
    0.09
    å®ĿçŁ³
    0.09
    mov
    0.09
    å½ĵåīįä½įç½®
    0.09
    ist
    0.09
    ç¿°
    0.08
    åĵij
    0.08
    è¶Ł
    0.08
    éĢ®
    0.08
    å¯ĴåĨ¬
    0.08
    Activations Density 0.317%

    No Known Activations