© 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. 17681
    Prev
    Next
    INDEX
    Explanations

    list items or instructions

    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
    åıĪæĺ¯
    -0.10
    åıĪæľī
    -0.09
    é¦ĸåħĪè¦ģ
    -0.09
    haar
    -0.09
    omas
    -0.09
    æŁ¥çľĭ详æĥħ
    -0.09
    ä¸Ģæĸ¹éĿ¢
    -0.09
    åıĪè¦ģ
    -0.08
    culator
    -0.08
    -born
    -0.08
    POSITIVE LOGITS
    çŃīçŃī
    0.11
    对人ä½ĵ
    0.10
    å¯¹æľªæĿ¥
    0.09
    以åıĬ
    0.09
     ÑģобÑģÑĤвенно
    0.09
     possibly
    0.08
    anst
    0.08
    èĩ³äºİ
    0.08
    伪
    0.08
    å°ıèħ¿
    0.08
    Activations Density 0.086%

    No Known Activations