© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21985
    Prev
    Next
    INDEX
    Explanations

    song titles often starting with quotes

    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
    ouri
    -0.09
    essim
    -0.09
    çļĦéĤ£ç§į
    -0.09
    æݨçIJĨ
    -0.09
    _NM
    -0.08
    errick
    -0.08
    ImageData
    -0.08
    LER
    -0.08
     WARRANTIES
    -0.08
    å¿«æĬ¥
    -0.08
    POSITIVE LOGITS
    ç§ĺ书éķ¿
    0.10
    ivet
    0.09
    åī¯ç§ĺ书éķ¿
    0.09
    天使
    0.08
    åijĪ
    0.08
    "
    0.08
    主å¸Ń
    0.08
    触
    0.08
    ä¹ĥ
    0.08
    æĻ®åıĬ
    0.08
    Activations Density 0.163%

    No Known Activations