© 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. 32843
    Prev
    Next
    INDEX
    Explanations

    testimonial, testimony, questionnaire

    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
    usan
    -0.09
    åIJįåı«
    -0.09
    à¹Ĩ
    -0.09
    iness
    -0.09
    lings
    -0.09
    éĿĽ
    -0.08
    strap
    -0.08
    主æĦı
    -0.08
    instein
    -0.08
     combin
    -0.08
    POSITIVE LOGITS
    ouro
    0.09
    åµĺ
    0.09
     forthcoming
    0.09
    irit
    0.09
    anes
    0.09
    anova
    0.08
    é£ŀè¡Įåijĺ
    0.08
    åĪ¶åº¦æĶ¹éĿ©
    0.08
    æĿĮ
    0.08
    arie
    0.08
    Activations Density 0.008%

    No Known Activations