© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17401
    Prev
    Next
    INDEX
    Explanations

    firsthand knowledge or experience

    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
    .named
    -0.10
    飶
    -0.09
    ijk
    -0.09
    寸
    -0.09
    æݥ管
    -0.09
    åĪĨæĺİ
    -0.09
    åİ®
    -0.09
    ushi
    -0.09
    æī¾äºĨ
    -0.08
    fund
    -0.08
    POSITIVE LOGITS
    åºķæ°Ķ
    0.10
     опÑĭ
    0.10
    çļĦç»ıéªĮ
    0.10
    ç»ıéªĮ
    0.10
     experience
    0.10
    亵
    0.10
     firsthand
    0.09
    ç»ıéªĮåĴĮ
    0.09
    亲身
    0.09
    ç¶ĵé©Ĺ
    0.09
    Activations Density 0.080%

    No Known Activations