© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51651
    Prev
    Next
    INDEX
    Explanations

    proportions and fractions

    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
    æıĨ
    -0.11
    owell
    -0.09
    åİŁæ²¹
    -0.09
    ç¥Ł
    -0.09
    ä¸Ĭåįĥ
    -0.09
    çļĦ对象
    -0.09
    è¯Ħè®®
    -0.09
    èĶ«
    -0.09
    å¹´åĨħ
    -0.08
    .Positive
    -0.08
    POSITIVE LOGITS
    ä¸ĢåįĬ
    0.21
    ä¸īåĪĨ
    0.18
    ä¸īåĪĨä¹ĭä¸Ģ
    0.18
    çĻ¾åĪĨä¹ĭ
    0.17
    ä¸Ģéĥ¨åĪĨ
    0.16
    çļĦä¸Ģéĥ¨åĪĨ
    0.12
    çĻ¾åĪĨçĻ¾
    0.11
    half
    0.11
    è¿Ļéĥ¨åĪĨ
    0.11
    -thirds
    0.10
    Activations Density 0.060%

    No Known Activations