© 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. 55760
    Prev
    Next
    INDEX
    Explanations

    certainty and affirmation

    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
    好ä¸į好
    -0.10
    ä»Ģä¹ĪæĦıæĢĿ
    -0.10
     ÑģобÑģÑĤвенно
    -0.09
    .Messaging
    -0.09
     Sov
    -0.09
     Caul
    -0.09
    åĶ
    -0.09
    (exc
    -0.08
    æ¯Ķè¾ĥç®Ģåįķ
    -0.08
    ile
    -0.08
    POSITIVE LOGITS
     definitely
    0.19
     Definitely
    0.17
    èĤ¯å®ļ
    0.16
    èĤ¯å®ļæĺ¯
    0.16
     certainly
    0.16
    å¿ħå®ļ
    0.15
    èĤ¯å®ļä¼ļ
    0.15
    ä¸Ģå®ļä¼ļ
    0.14
    å¿ħçĦ¶ä¼ļ
    0.14
    ä¸Ģå®ļèĥ½
    0.13
    Activations Density 0.045%

    No Known Activations