© 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. 63585
    Prev
    Next
    INDEX
    Explanations

    redistribute it

    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
     pouvoir
    -0.13
    èĥ½å¤Łåľ¨
    -0.13
    èĥ½çľĭåĪ°
    -0.12
    èĥ½å¤Ł
    -0.12
    åı¯è¾¾
    -0.12
    èĥ½åľ¨
    -0.11
    åı¯è§ģ
    -0.11
     ability
    -0.11
    å¸ĮæľĽèĥ½å¤Ł
    -0.11
    èĥ½å¤ł
    -0.10
    POSITIVE LOGITS
    ä¹ŁåºĶ该
    0.16
    åģļåĪ°
    0.13
    ä¹°åĪ°
    0.13
     anytime
    0.12
    't
    0.12
    çľĭåĩº
    0.11
    é¢Ħè§ģ
    0.11
     easily
    0.11
    ä»»ä½ķä¸Ģ个
    0.11
    æĦŁåıĹåĪ°
    0.11
    Activations Density 0.994%

    No Known Activations