© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36335
    Prev
    Next
    INDEX
    Explanations

    quoted words

    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
    plib
    -0.10
    è¹Ļ
    -0.09
    /******************************************************************************/↵
    -0.09
    adera
    -0.09
    agar
    -0.09
    æĢİä¹Īèĥ½
    -0.09
     euler
    -0.09
    .Creator
    -0.09
    æĹłæķ°æ¬¡
    -0.09
    æĥ®
    -0.09
    POSITIVE LOGITS
    幸ç¦ıæĦŁ
    0.10
    åĪĩåħ¥
    0.09
    ãģ¨ãģª
    0.08
    ings
    0.08
     Bethesda
    0.08
    ertia
    0.08
    åįģä¸īäºĶ
    0.08
    etics
    0.08
    æ¦ľ
    0.08
    ä»»æĢ§
    0.08
    Activations Density 0.121%

    No Known Activations