© 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. 10853
    Prev
    Next
    INDEX
    Explanations

    confidence and trust

    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
    ä¸ŀ
    -0.12
    æĻºèĥ½åĮĸ
    -0.10
    èģĶ绾
    -0.09
    çĬĢ
    -0.09
    _UT
    -0.09
    å®Ľ
    -0.09
    åıĺå½¢
    -0.09
    è°
    -0.09
    eselect
    -0.09
    æ¸Ĺ
    -0.08
    POSITIVE LOGITS
    ä¿¡å¿ĥ
    0.31
    ä¿¡ä»»
    0.28
     confidence
    0.26
    ä¿¡èµĸ
    0.25
    çļĦä¿¡å¿ĥ
    0.25
    confidence
    0.23
     Confidence
    0.23
     trust
    0.22
    çļĦä¿¡ä»»
    0.22
    èĩªä¿¡
    0.20
    Activations Density 0.048%

    No Known Activations