© 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. 52853
    Prev
    Next
    INDEX
    Explanations

    simply followed by a verb

    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
    æŀķ
    -0.10
    åĩłä¹İæīĢæľī
    -0.10
    åĩłä¹İ
    -0.10
    leta
    -0.10
    ä¹ĭæīĢ以
    -0.10
    lier
    -0.09
    èĤ¼
    -0.09
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.08
    isplay
    -0.08
    IMO
    -0.08
    POSITIVE LOGITS
    说æĪij
    0.11
    é»ĺé»ĺ
    0.09
    à¹ģà¸Ħ
    0.09
    edin
    0.09
    oid
    0.08
    ä¸įä¸Ĭ
    0.08
    à¹ģห
    0.08
    antly
    0.08
    è°ģéĥ½
    0.08
     Merkel
    0.08
    Activations Density 0.012%

    No Known Activations