© 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. 50794
    Prev
    Next
    INDEX
    Explanations

    reading or software projects

    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
    æİĴæ°Ķ
    -0.09
    PIC
    -0.09
    åĴĮåľ°åĮº
    -0.09
    ÅĤow
    -0.09
     chóng
    -0.09
    æĭĽåij¼
    -0.08
    rok
    -0.08
    é¦į
    -0.08
    é©°
    -0.08
    _GATE
    -0.08
    POSITIVE LOGITS
    illa
    0.10
    çij¶
    0.09
    è¿¢
    0.09
     comb
    0.09
    تاب
    0.08
    æĬ¬èµ·
    0.08
     tal
    0.08
    åħ±åĴĮ
    0.08
     Tal
    0.08
    opal
    0.08
    Activations Density 0.008%

    No Known Activations