© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21419
    Prev
    Next
    INDEX
    Explanations

    Tamil words and names

    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
    éĥ«
    -0.10
     Damascus
    -0.09
    å¹ħ
    -0.09
    ä¸Ģæł·çļĦ
    -0.09
    æĴº
    -0.09
    findFirst
    -0.09
    éĺĴ
    -0.08
    fulness
    -0.08
    åĴĮåıijå±ķ
    -0.08
    èı°
    -0.08
    POSITIVE LOGITS
     Tamil
    0.11
     Chennai
    0.10
    ç»įåħ´
    0.10
     tamil
    0.10
    Scheme
    0.09
    è¶Ĭ
    0.09
    æµĻæ±Łçľģ
    0.09
    å¥ĩçijŀ
    0.09
    _scheme
    0.09
    ä¹Ŀæ±Ł
    0.09
    Activations Density 0.108%

    No Known Activations