© 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. 20483
    Prev
    Next
    INDEX
    Explanations

    RTW trip

    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
    éķ¿å¾Ĺ
    -0.12
    elcome
    -0.09
    ãĤĪãģĨãģª
    -0.08
    ICENSE
    -0.08
    ãģķãģ¦
    -0.08
    ibrary
    -0.08
    ToAdd
    -0.08
    ãģĻãģ§ãģ«
    -0.08
    æŶåĢĻ
    -0.08
    ernel
    -0.08
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.14
    åħ¶å®ĥ
    0.14
    æį¢åı¥è¯Ŀ说
    0.12
    ËĪ
    0.11
    áIJł
    0.11
    æĪĸèĢħ说
    0.11
    ËĮ
    0.10
    acles
    0.10
    ä½£
    0.10
    ä¾Ī
    0.10
    Activations Density 0.112%

    No Known Activations