© 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. 26088
    Prev
    Next
    INDEX
    Explanations

    without limitation

    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
    -0.10
     Carpet
    -0.10
    èĦį
    -0.09
     вообÑīе
    -0.09
    å°ıå¿ĥ
    -0.08
    èĽ°
    -0.08
    quot
    -0.08
    åıĶ
    -0.08
    æĪijçļĦå¿ĥ
    -0.08
    å¾Ĺ天
    -0.08
    POSITIVE LOGITS
    以为
    0.10
    以çĤº
    0.09
    pio
    0.09
    ä¸įéĻIJ
    0.09
    /goto
    0.08
    acio
    0.08
    usty
    0.08
    æ¡ĥ
    0.08
    PLATFORM
    0.08
     adına
    0.08
    Activations Density 0.049%

    No Known Activations