© 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. 40085
    Prev
    Next
    INDEX
    Explanations

    give you/a/me

    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
    ãģĦãģĭ
    -0.10
    amp
    -0.10
    å±ij
    -0.09
    ight
    -0.09
    ifes
    -0.09
    èĥ½å¾ĹåĪ°
    -0.09
    ixel
    -0.09
    人士
    -0.09
    uart
    -0.09
    resses
    -0.09
    POSITIVE LOGITS
    aways
    0.12
    äºĨä¸Ģ
    0.12
    侧ç»ĵæŀĦæĢ§
    0.12
     us
    0.11
    äºĨä¸Ģåı¥
    0.10
    äºĨä¸Ģ份
    0.10
     rise
    0.10
    ëģĶ
    0.10
     phép
    0.09
    íĽĪ
    0.09
    Activations Density 0.058%

    No Known Activations