© 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. 5840
    Prev
    Next
    INDEX
    Explanations

    SEO and content structure

    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
    ç»ĻåĬĽ
    -0.10
    交åıĭ
    -0.09
    马路
    -0.09
    èijĨ
    -0.09
    èµŃ
    -0.09
    éĢĨè¡Į
    -0.09
    chant
    -0.09
    çĶŁæ´»åŀĥåľ¾
    -0.09
    请æķĻ
    -0.08
    ilda
    -0.08
    POSITIVE LOGITS
    å¥ī
    0.10
    .writer
    0.09
    æĸĩç«ł
    0.09
    æĴ°åĨĻ
    0.08
     SEO
    0.08
     writers
    0.08
    æĺİæĺ¾
    0.08
    _srv
    0.08
    /meta
    0.08
    airo
    0.08
    Activations Density 0.161%

    No Known Activations