© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63930
    Prev
    Next
    INDEX
    Explanations

    constraint / constraints

    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
    Negative Logits
    çĶĦ
    -0.09
    auce
    -0.09
    ãĥĩãĤ£ãĥ³ãĤ°
    -0.09
    hood
    -0.09
    å¾ĹçĽĬ
    -0.08
    ÑĪе
    -0.08
    ç§
    -0.08
    CADE
    -0.08
    ickness
    -0.08
    便åĪ©åºĹ
    -0.08
    POSITIVE LOGITS
    约æĿŁ
    0.15
    .Constraint
    0.14
     constraints
    0.13
     Constraints
    0.13
    Constraints
    0.13
    constraints
    0.12
    .constraints
    0.11
    æĿ¡ä»¶ä¸ĭ
    0.11
    æĿ¡ä»¶
    0.11
    .constraint
    0.10
    Activations Density 0.049%

    No Known Activations