© 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. 11639
    Prev
    Next
    INDEX
    Explanations

    removal of things

    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
    ä¸ĺ
    -0.10
    å°Ĭéĩį
    -0.09
    ä¸įçķĻ
    -0.09
    è¶ĬæĿ¥è¶Ĭé«ĺ
    -0.09
    ä¸Ī
    -0.09
    à¹Ħล
    -0.09
    两åij¨
    -0.08
    FIELDS
    -0.08
    éķŃ
    -0.08
    equip
    -0.08
    POSITIVE LOGITS
     ú
    0.10
    妨ç¢į
    0.09
    æĮij
    0.08
    éļħ
    0.08
    并对
    0.08
    enberg
    0.08
    å¯Ħ
    0.08
    å°¬
    0.08
    èĭij
    0.07
    并å°Ĩ
    0.07
    Activations Density 0.032%

    No Known Activations