© 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. 56989
    Prev
    Next
    INDEX
    Explanations

    Plattsburgh, New Yorker, UR, BSD

    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
    inflate
    -0.09
    åĨ²çªģ
    -0.09
     Dimit
    -0.08
    åĵĦ
    -0.08
    å¨ĥå¨ĥ
    -0.08
    à¹ģà¸ģ
    -0.08
    empo
    -0.08
    åijĬåĪ«
    -0.08
     плаÑĤ
    -0.08
    æĺ¯å¯¹
    -0.08
    POSITIVE LOGITS
    éĢĢ
    0.09
    å¾®åįļ
    0.09
     Tough
    0.09
    anced
    0.09
     Bloody
    0.08
     BIN
    0.08
    ç²¹
    0.08
     Clearance
    0.08
     Posting
    0.08
    	TokenName
    0.08
    Activations Density 0.001%

    No Known Activations