© 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. 21289
    Prev
    Next
    INDEX
    Explanations

    going off topic

    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
    ipe
    -0.09
    éļ±
    -0.09
    icl
    -0.09
    Collapsed
    -0.09
    åŀĦ
    -0.08
    åĮĸè¿Ľç¨ĭ
    -0.08
    åĽ°éļ¾
    -0.08
    PRIMARY
    -0.08
     Colleg
    -0.08
    稹
    -0.08
    POSITIVE LOGITS
    å²Ķ
    0.14
    个åĪ«
    0.12
     det
    0.12
    åģı离
    0.11
    æĹłåħ³
    0.11
    èĢ½
    0.11
    é¢Ŀå¤ĸ
    0.10
    æļĤç¼ĵ
    0.10
    å®ķ
    0.10
    åĪĨæķ£
    0.10
    Activations Density 0.076%

    No Known Activations