© 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. 1137
    Prev
    Next
    INDEX
    Explanations

    insurance plans

    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
    å¨Ĩ
    -0.12
    æ¦ľ
    -0.11
    halb
    -0.10
    ä¸Ģ个éĩįè¦ģ
    -0.10
    ya
    -0.10
    ../../
    -0.09
    管å§Ķä¼ļ
    -0.09
    iting
    -0.09
    天涯
    -0.09
    urd
    -0.09
    POSITIVE LOGITS
    isphere
    0.17
    ãĥĭãĥ³ãĤ°
    0.13
    etary
    0.12
     sobie
    0.10
    ète
    0.10
    ings
    0.10
    妥
    0.10
    fort
    0.10
    ural
    0.09
    enberg
    0.09
    Activations Density 0.039%

    No Known Activations