© 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. 9942
    Prev
    Next
    INDEX
    Explanations

    appear

    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
    ë¶Ģ
    -0.11
    gone
    -0.10
    ÑĢин
    -0.10
    åĩºèº«
    -0.09
    busters
    -0.09
    gettext
    -0.09
     Bom
    -0.09
    æ¡ĤèĬ±
    -0.09
    è¦ģéĹ»
    -0.09
    åľ¨ä¹İ
    -0.09
    POSITIVE LOGITS
    .rc
    0.09
    lassen
    0.09
     embr
    0.08
    æĸ°çļĦ
    0.08
    oto
    0.08
    èĨº
    0.08
    éªĤ
    0.08
    /share
    0.08
    /embed
    0.08
    ä¸įäºĨ
    0.08
    Activations Density 0.030%

    No Known Activations