© 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. 27683
    Prev
    Next
    INDEX
    Explanations

    famous last names

    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
    é¡·
    -0.10
    æĢ»çIJĨ
    -0.10
    磬
    -0.10
    èij£äºĭä¼ļ
    -0.09
    oris
    -0.09
    湫
    -0.09
    鸵
    -0.09
    æݬ
    -0.09
    åIJŀ
    -0.09
    è¡ħ
    -0.09
    POSITIVE LOGITS
    çĽ²
    0.09
    Respond
    0.08
    æĻ¦
    0.08
    worthy
    0.07
    积æ·Ģ
    0.07
     sỼm
    0.07
    ogue
    0.07
    ä¸į失
    0.07
    ket
    0.07
     há»ģ
    0.07
    Activations Density 0.076%

    No Known Activations