© 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. 51638
    Prev
    Next
    INDEX
    Explanations

    do not need to

    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
    æķ²
    -0.09
    ä¸įå½ĵ
    -0.08
     rather
    -0.08
    éģĩåĪ°äºĨ
    -0.08
    æĬ½
    -0.08
    è¿Ł
    -0.08
    ä¸įæĦ¿
    -0.08
     Intercept
    -0.08
    åħĨ
    -0.08
    indi
    -0.08
    POSITIVE LOGITS
     обÑıзаÑĤелÑĮно
    0.14
    æīįåı¯ä»¥
    0.14
    æīįèĥ½
    0.13
     necessarily
    0.13
    çIJĨä¼ļ
    0.12
    ãģªãģıãģ¦ãĤĤ
    0.12
    æľīä»»ä½ķ
    0.11
    éĿŀè¦ģ
    0.11
    æīįèĥ½å¤Ł
    0.11
    å°±èĥ½
    0.11
    Activations Density 0.068%

    No Known Activations