© 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. 23389
    Prev
    Next
    INDEX
    Explanations

    weather conditions

    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
    èĪĮå°ĸ
    -0.10
     оÑĤдÑĭÑħ
    -0.09
    è°ª
    -0.09
    竽
    -0.08
    indle
    -0.08
    çļĦä¹IJ趣
    -0.08
    æ¾į
    -0.08
    è°Ĺ
    -0.08
    é«ĺ度
    -0.08
    åIJĮåѦ
    -0.08
    POSITIVE LOGITS
    çĶŁæ´»ä¸Ń
    0.09
    åľ»
    0.09
    èµ°
    0.09
    ä¸Ģ线
    0.08
    alach
    0.08
    ä½ľåĵģåĨħ容
    0.08
    escription
    0.08
    人æĢ§
    0.08
    æħĪåĸĦ
    0.08
    precision
    0.08
    Activations Density 0.006%

    No Known Activations