© 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. 48814
    Prev
    Next
    INDEX
    Explanations

    in my head

    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
    åºŁè¯Ŀ
    -0.09
     Ray
    -0.09
    åIJĪæ³ķ
    -0.09
    æĦį
    -0.09
    å¨ģ
    -0.08
     вообÑīе
    -0.08
    æĽĿåħī
    -0.08
    åĵ§
    -0.08
     Rochester
    -0.08
    æĮĩçĤ¹
    -0.08
    POSITIVE LOGITS
    èĦijæµ·
    0.22
    å¿ĥä¸ŃçļĦ
    0.20
    èĦijæµ·ä¸Ń
    0.19
    å¿ĥä¸Ń
    0.17
    èĦijåŃIJéĩĮ
    0.17
    å¿ĥéĩĮ
    0.15
     mental
    0.15
    èħ¦
    0.14
     minds
    0.14
     mind
    0.14
    Activations Density 0.199%

    No Known Activations