© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51805
    Prev
    Next
    INDEX
    Explanations

    more the more

    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
    è¸Į
    -0.09
    å¾Īä½İ
    -0.09
    æĤŁ
    -0.08
    è¶³å¤Ł
    -0.08
     minded
    -0.08
    illet
    -0.08
    å¾Īæĺ¯
    -0.08
    ä¸įåĨį
    -0.07
    ient
    -0.07
    oho
    -0.07
    POSITIVE LOGITS
    å°±è¶Ĭ
    0.19
    è¶Ĭ好
    0.16
    è¶Ĭæĺ¯
    0.14
    è¶Ĭå¤ļ
    0.13
    è¶Ĭ大
    0.12
    æĹłç¼Ŀ
    0.11
    è¶Ĭ
    0.11
    è¶Ĭé«ĺ
    0.11
    anza
    0.10
    èļģ
    0.09
    Activations Density 0.049%

    No Known Activations