© 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. 49065
    Prev
    Next
    INDEX
    Explanations

    questions about numbers and math

    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
    辩æĬ¤
    -0.10
    è¿©
    -0.10
    çģ
    -0.09
    æľĹ诵
    -0.09
    çĻŀ
    -0.09
    otropic
    -0.09
    é³Ħ
    -0.09
    ê¶ģ
    -0.09
    è¡®
    -0.09
    ä¸Ńæŀ¢
    -0.09
    POSITIVE LOGITS
    roman
    0.09
    bt
    0.09
    ä¸Ģå¹´ä¸Ģ度
    0.08
    bat
    0.08
    zie
    0.08
    timezone
    0.08
    arness
    0.07
     Copyright
    0.07
    ory
    0.07
    浸
    0.07
    Activations Density 0.159%

    No Known Activations