© 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. 54297
    Prev
    Next
    INDEX
    Explanations

    musical notes or chords, technical notation

    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
    éĤ£æł·
    -0.09
    æµij身
    -0.09
    åĴĮåľ°åĮº
    -0.09
    åħīéĺ´
    -0.09
    éĤ£ä¸Ģ
    -0.08
    éĶ¥
    -0.08
    线ä¸Ĭ线ä¸ĭ
    -0.08
    顽
    -0.08
    rix
    -0.08
    é«ĺä½į
    -0.08
    POSITIVE LOGITS
     followed
    0.13
    æİ¥çĿĢ
    0.12
    çĦ¶åIJİ
    0.12
    again
    0.11
     again
    0.11
    çĦ¶å¾Į
    0.10
     Ñģнова
    0.10
    åįĩ温
    0.09
    æİ¥èijĹ
    0.09
    çĦ¶åIJİåĨį
    0.09
    Activations Density 0.167%

    No Known Activations