© 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. 61601
    Prev
    Next
    INDEX
    Explanations

    timing variability

    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
    积
    -0.11
    èµĿ
    -0.11
    çĥ«
    -0.10
    车祸
    -0.09
    èĽĬ
    -0.09
    reh
    -0.09
    åºŁ
    -0.08
    atile
    -0.08
    æݨéĶĢ
    -0.08
    è¿Ļä¸Ģå¹´
    -0.08
    POSITIVE LOGITS
    å°Ĩ继ç»Ń
    0.09
    æĴ¤ç¦»
    0.09
    roma
    0.09
    é¢Ħ计å°Ĩ
    0.09
    å¨ģåĬĽ
    0.09
    çĻ»éĻĨ
    0.09
    çĬģ
    0.08
    纾
    0.08
    æ¶Īæģ¯ç§°
    0.08
    æľ¬èº«çļĦ
    0.08
    Activations Density 0.047%

    No Known Activations