© 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. 22502
    Prev
    Next
    INDEX
    Explanations

    on the table, any question, open, off record

    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
    æĸ°æĶ¿
    -0.10
    æģĴ
    -0.10
    oman
    -0.09
    jing
    -0.09
    ACY
    -0.09
    èIJ¥è¿IJ
    -0.09
    éī´
    -0.09
     اÙĦÙĤض
    -0.09
    èŃĺ
    -0.09
    _intr
    -0.09
    POSITIVE LOGITS
    ç¦ģåĮº
    0.12
     subject
    0.10
    çķħ
    0.10
     Subject
    0.10
    é²ľæ´»
    0.09
    大家åı¯ä»¥
    0.09
    æĭ¿æĿ¥
    0.09
     taboo
    0.09
    åı¯ä¾Ľ
    0.09
     open
    0.09
    Activations Density 0.072%

    No Known Activations