© 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. 18819
    Prev
    Next
    INDEX
    Explanations

    to educate and train students

    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
    åĨħ容ç®Ģä»ĭ
    -0.09
    è¿ŀå¤ľ
    -0.08
    åĪĿè¡·
    -0.08
    8
    -0.08
     jun
    -0.07
    åıªå¥½
    -0.07
    æĥŁ
    -0.07
    å·¥ä½ľä»»åĬ¡
    -0.07
    æīĭéĩĮ
    -0.07
    igh
    -0.07
    POSITIVE LOGITS
    å°º
    0.10
    icken
    0.10
    éħ¬
    0.09
    à¹Į
    0.09
    idine
    0.09
    __.__
    0.09
    pler
    0.09
    é¼ĵèĪŀ
    0.09
    .assertRaises
    0.09
    ноп
    0.09
    Activations Density 0.226%

    No Known Activations