© 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. 5093
    Prev
    Next
    INDEX
    Explanations

    events and circumstances

    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
    IVAL
    -0.10
    æĿĥå¨ģ
    -0.10
    åīĭ
    -0.10
    Ñģон
    -0.10
    è¿ĻæĶ¯
    -0.09
    æĿĪ
    -0.09
     unseen
    -0.09
    ONY
    -0.09
    _lex
    -0.09
    æ¿Ģ
    -0.09
    POSITIVE LOGITS
    ä»ij
    0.09
    âģ½
    0.08
    èĩªè´Ł
    0.08
    大夫
    0.08
     hand
    0.08
    å°ĸ
    0.08
    æĤ£
    0.08
    æŃ
    0.08
    _cal
    0.08
    rain
    0.08
    Activations Density 0.007%

    No Known Activations