© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48551
    Prev
    Next
    INDEX
    Explanations

    remarkable

    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
     вÑģÑı
    -0.09
    liness
    -0.09
    esti
    -0.09
    amic
    -0.09
    大å±Ģ
    -0.09
    argc
    -0.08
    æ»Ĥ
    -0.08
    bie
    -0.08
    é¢ĸ
    -0.08
    ราย
    -0.08
    POSITIVE LOGITS
    eting
    0.12
    人士
    0.11
    ETING
    0.10
     üzere
    0.10
    ä¸Ģç«Ļ
    0.10
    ä¹ĭä½ľ
    0.10
    ness
    0.09
    ç¥ŀéĢļ
    0.09
    iveness
    0.09
    ä¹ĭå¤Ħ
    0.09
    Activations Density 0.008%

    No Known Activations