© 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. 57819
    Prev
    Next
    INDEX
    Explanations

    saying that

    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
    kus
    -0.08
    æĭ¿åĩº
    -0.08
    çŁŃçŁŃ
    -0.08
     Lac
    -0.08
    åĨĻä½ľ
    -0.08
    ers
    -0.08
    Æ°a
    -0.08
    èĽĨ
    -0.08
    or
    -0.08
    è¹²
    -0.08
    POSITIVE LOGITS
    å¹´ä¹ĭ
    0.10
    ä»Ģä¹Īåij¢
    0.09
    è°£
    0.09
    çĶ¢
    0.09
    红æŀ£
    0.09
    çĩĶ
    0.09
    äºĨä¸įå°ij
    0.09
    é¢ĩ为
    0.09
    é©¿
    0.09
    产
    0.09
    Activations Density 0.049%

    No Known Activations