© 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. 52786
    Prev
    Next
    INDEX
    Explanations

    House of Commons and Chambers of Deputies

    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
    èį«
    -0.09
    edin
    -0.09
    èĭį
    -0.09
    æ¾¹
    -0.09
    edriver
    -0.08
    ç¾İæĻ¯
    -0.08
    åį·
    -0.08
     Chronicle
    -0.08
    ä¼ŀ
    -0.08
     simp
    -0.08
    POSITIVE LOGITS
    å¸ĥ
    0.10
    åĽ½ä¼ļ
    0.10
    è®®äºĭ
    0.09
    审议éĢļè¿ĩ
    0.09
     nghá»ĭ
    0.09
     brink
    0.09
    审议
    0.09
    座ä½į
    0.09
    è®®åijĺ
    0.09
    å¸Ń
    0.08
    Activations Density 0.154%

    No Known Activations