© 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. 6620
    Prev
    Next
    INDEX
    Explanations

    learn more about

    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
    oster
    -0.09
    olk
    -0.09
    .vs
    -0.09
    down
    -0.08
    çݩ家æĿ¥è¯´
    -0.08
    VICE
    -0.08
    Ñĥн
    -0.08
     wÅĤaÅĽnie
    -0.08
    iments
    -0.08
    iment
    -0.08
    POSITIVE LOGITS
     about
    0.10
    æľīæĽ´å¥½çļĦ
    0.10
    é¢Ĩä¼ļ
    0.09
    pty
    0.09
    ocha
    0.09
    娣
    0.09
    äºĭ迹
    0.08
    łéĻ¤
    0.08
    æľīåĬ©
    0.08
    èĶļ
    0.08
    Activations Density 0.007%

    No Known Activations