© 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. 56805
    Prev
    Next
    INDEX
    Explanations

    questions and advice

    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
    çī¹åĪ«å£°æĺİ
    -0.10
    æĶĺ
    -0.10
    åĪª
    -0.10
    å¯ħ
    -0.09
    ç»ŀ
    -0.09
    æĪIJçĨŁçļĦ
    -0.09
    æĪIJçĨŁ
    -0.09
     ëĵ¤
    -0.09
    æĶ¶èİ·
    -0.09
    为é¦ĸ
    -0.09
    POSITIVE LOGITS
    è´Ń车
    0.10
     Karn
    0.10
    çľĭçĹħ
    0.10
    åıĤè§Ĥ
    0.10
    æĬ¥èĢĥ
    0.09
    游çİ©
    0.09
    åŀĤ
    0.09
    个人
    0.09
    è§Ĥçľĭ
    0.09
     Conspiracy
    0.08
    Activations Density 0.572%

    No Known Activations