© 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. 35614
    Prev
    Next
    INDEX
    Explanations

    held events and locations

    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
    æµİ
    -0.09
    Christmas
    -0.09
    éĢĨ
    -0.09
    佩
    -0.09
    æģ¬
    -0.09
    endas
    -0.09
    elve
    -0.08
    åѤ
    -0.08
    è¿ĽæĿ¥
    -0.08
    æĬķåħ¥åĪ°
    -0.08
    POSITIVE LOGITS
    举è¡ĮçļĦ
    0.18
    åľ°çĤ¹
    0.15
    举åĬŀçļĦ
    0.14
    å®īæİĴ
    0.13
    举è¡Į
    0.13
     location
    0.13
    举åĬŀ
    0.12
    æĪIJåĬŁä¸¾åĬŀ
    0.12
    åı¬å¼Ģ
    0.12
    åıijçĶŁåľ¨
    0.11
    Activations Density 0.195%

    No Known Activations