© 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. 8811
    Prev
    Next
    INDEX
    Explanations

    pause or using

    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
    èĥĮçĿĢ
    -0.09
    åĻªå£°
    -0.09
    shoot
    -0.09
    ittings
    -0.09
    ilate
    -0.08
    miss
    -0.08
    bing
    -0.08
    åī¯ä¸»ä»»
    -0.08
    shaw
    -0.08
    åĻª
    -0.08
    POSITIVE LOGITS
    Ãłng
    0.11
     Pause
    0.10
    æѤåĪ»
    0.10
    á»ijc
    0.09
    èĦļæŃ¥
    0.09
    _pause
    0.09
     deliber
    0.09
     ÐijеÑģ
    0.09
    太ä¹ħ
    0.09
    umu
    0.09
    Activations Density 0.012%

    No Known Activations