© 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. 10900
    Prev
    Next
    INDEX
    Explanations

    relationship and time

    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
    åī¥ç¦»
    -0.10
    åħĪéĶĭ
    -0.09
    ä¼ŀ
    -0.09
    驺
    -0.09
    akra
    -0.09
    ä¸Ģå¥Ĺ
    -0.08
    æł·çļĦ
    -0.08
    æ¯ı个人éĥ½
    -0.08
    èĥ±
    -0.08
    é£
    -0.08
    POSITIVE LOGITS
    _regression
    0.10
    éĶĻè¿ĩ
    0.10
    éĶĻè¿ĩäºĨ
    0.09
    身å¿ĥåģ¥åº·
    0.09
     Squ
    0.09
     squ
    0.09
    Regression
    0.08
    èĵ¼
    0.08
     egreg
    0.08
     conjug
    0.08
    Activations Density 0.034%

    No Known Activations