© 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. 56838
    Prev
    Next
    INDEX
    Explanations

    admission or denial

    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¸įæľį
    -0.11
    ä¸įä¿¡
    -0.09
    ä»İä¸Ń
    -0.09
    æ²½
    -0.08
    èµŀ
    -0.08
    é¬ĵ
    -0.08
    对èĩªå·±çļĦ
    -0.08
    被æ·ĺæ±°
    -0.08
    çºł
    -0.08
    躯
    -0.08
    POSITIVE LOGITS
    äºĪ
    0.12
    åıijæĶ¾
    0.11
    åıĹçIJĨ
    0.10
    ä¸į让
    0.10
     Blo
    0.10
    chai
    0.10
    ç»Ļä»ĸ们
    0.10
    æݥ纳
    0.10
    æİĪ
    0.10
    itia
    0.10
    Activations Density 0.100%

    No Known Activations