© 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. 21969
    Prev
    Next
    INDEX
    Explanations

    intensifier (really)

    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
    ëĬIJ
    -0.09
    ä¸ĢäºĽ
    -0.09
    GED
    -0.09
    la
    -0.08
    ions
    -0.08
    anz
    -0.08
    asel
    -0.08
    åıĺçİ°
    -0.08
    åĴĮæĶ¯æĮģ
    -0.08
    çģµ
    -0.07
    POSITIVE LOGITS
    æ¯ıä¸Ģä½į
    0.12
    æĦıä¹īä¸Ĭ
    0.11
    çŁ¥å·±
    0.10
    çľĭä½ł
    0.09
    oug
    0.09
    ç§ijæĬĢèĤ¡ä»½
    0.09
    åŃ³
    0.09
    æĸĹå¿Ĺ
    0.09
    éļıå¤Ħ
    0.09
    æ¯Ľå·¾
    0.09
    Activations Density 0.021%

    No Known Activations