© 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. 39640
    Prev
    Next
    INDEX
    Explanations

    for or to specific phrases

    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
    æ´ŀ
    -0.10
    çĵ¶åŃIJ
    -0.09
    ä¸įå¾Ĺå·²
    -0.09
    éĿłçĿĢ
    -0.09
     stereotype
    -0.09
    åºŁæŧ
    -0.08
    usk
    -0.08
    icit
    -0.08
    çķ´
    -0.08
    å¤ļå¤ļ
    -0.08
    POSITIVE LOGITS
    åĪ¨
    0.10
    æīĭæĦŁ
    0.10
    çŃ¾çº¦
    0.09
    มà¸Ńà¸ļ
    0.09
    åħ¬åijĬ
    0.09
    ç»´æĿĥ
    0.09
    елÑı
    0.09
    失åİ»äºĨ
    0.09
    毡
    0.09
    åħ¬çĽĬæĢ§
    0.08
    Activations Density 0.021%

    No Known Activations