© 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. 1140
    Prev
    Next
    INDEX
    Explanations

    improving or reversing conditions

    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
    åı¸é©¬
    -0.10
    arme
    -0.09
    åı¸
    -0.09
    æ°ijéĹ´
    -0.09
    çĴŀ
    -0.09
     кнопк
    -0.08
    åĪ»èĭ¦
    -0.08
    æĭĹ
    -0.08
    ä¾µçĬ¯
    -0.08
    echa
    -0.08
    POSITIVE LOGITS
    çĢij
    0.09
    èµ·åĪ°
    0.09
    æĮ½åĽŀ
    0.09
    missions
    0.09
    geries
    0.09
    å¸ľ
    0.09
    cents
    0.09
    ä¸įèĩ³äºİ
    0.08
    ä¸įåĨį
    0.08
    使åij½
    0.08
    Activations Density 0.238%

    No Known Activations