© 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. 54049
    Prev
    Next
    INDEX
    Explanations

    for specific groups or durations

    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
    åŃ½
    -0.09
    otherapy
    -0.09
    enez
    -0.08
    åĽ¢å§Ķ
    -0.08
    çļĦåIJĮåѦ
    -0.08
    ä¸Ģå¹ħ
    -0.08
    è¡Įäºĭ
    -0.08
    累累
    -0.08
    åī²
    -0.08
    èį¼
    -0.08
    POSITIVE LOGITS
    baugh
    0.10
    endregion
    0.10
    éľī
    0.09
    模èĮĥ
    0.09
    éĹŃçݯ
    0.09
    å´Ľ
    0.09
    é¢Ĩ导干éĥ¨
    0.09
    çļĦåĪ©çĽĬ
    0.08
    女æĢ§
    0.08
    读æĩĤ
    0.08
    Activations Density 0.074%

    No Known Activations