© 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. 35510
    Prev
    Next
    INDEX
    Explanations

    Cinderella, Tinder, Cindy, Binder

    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
    nika
    -0.10
    inus
    -0.09
    满满
    -0.09
    岿
    -0.09
    uvwxyz
    -0.09
    inke
    -0.09
    å·¯
    -0.09
    rvine
    -0.09
    çľ¼çķĮ
    -0.09
    çĻ½éĵ¶
    -0.08
    POSITIVE LOGITS
    ãģ¾ãģ¾
    0.09
    æŁ³
    0.09
    ous
    0.09
    joy
    0.09
    åİ
    0.09
    boxing
    0.08
     formal
    0.08
    pon
    0.08
     Venez
    0.08
    .hm
    0.08
    Activations Density 0.003%

    No Known Activations