© 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. 9697
    Prev
    Next
    INDEX
    Explanations

    trailer

    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
    èĦ±
    -0.11
    èIJ§
    -0.10
    对éĿ¢
    -0.09
    ç¼Ļ
    -0.08
    夺
    -0.08
    lash
    -0.08
    _macros
    -0.08
    èħ°éĥ¨
    -0.08
    ections
    -0.08
    æĴ®
    -0.08
    POSITIVE LOGITS
    åħĪ导
    0.11
    é¢ĦåijĬ
    0.11
     trailer
    0.09
    æݨ广
    0.09
    æıIJåīį
    0.09
    欺éªĹ
    0.09
    åħĪè¡Į
    0.09
     testers
    0.09
    åħ¥åºĵ
    0.09
    .tt
    0.08
    Activations Density 0.117%

    No Known Activations