© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36909
    Prev
    Next
    INDEX
    Explanations

    `.gl` URLs followed by path

    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
     Sala
    -0.09
    flo
    -0.09
    èŀĥèŁ¹
    -0.09
    ä¸ĢçĻ¾å¤ļ
    -0.09
    çłį
    -0.08
    rais
    -0.08
    éĵ®
    -0.08
    åıijå±ķè¶ĭåĬ¿
    -0.08
    /comment
    -0.08
    é«ĺè´µ
    -0.08
    POSITIVE LOGITS
    æĥij
    0.10
    åħ¨éĿ¢èIJ½å®ŀ
    0.09
    身åIJİ
    0.08
    à¸ł
    0.08
    ستر
    0.08
    alyze
    0.08
    ments
    0.08
     Classics
    0.08
    ipse
    0.08
    filer
    0.08
    Activations Density 0.001%

    No Known Activations