© 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. 62137
    Prev
    Next
    INDEX
    Explanations

    horseback riding, plane rides, gliding

    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¿Ļ
    -0.11
    aked
    -0.10
    åIJijä¸Ĭ
    -0.09
    纷
    -0.09
    è¹²
    -0.09
    ç¬ijäºĨç¬ij
    -0.09
    æĺ§
    -0.09
    åĢĻ
    -0.09
    å¾Ģä¸Ĭ
    -0.09
    çĭ¡
    -0.08
    POSITIVE LOGITS
    åħľ
    0.11
    享åıĹ
    0.10
    æĦŁåıĹ
    0.10
    ä½ĵéªĮ
    0.10
    rides
    0.10
    ä½ĵä¼ļ
    0.10
    é«Ķé©Ĺ
    0.10
    èĴ¸æ±½
    0.09
    游è§Ī
    0.09
    å¥ĩå¼Ĥ
    0.09
    Activations Density 0.033%

    No Known Activations