© 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. 3121
    Prev
    Next
    INDEX
    Explanations

    stacking / stacked

    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
    forc
    -0.09
    æĢı
    -0.09
    .utf
    -0.08
     Kauf
    -0.08
    .Commit
    -0.08
    isse
    -0.08
    ãģ©ãģĵãĤį
    -0.08
    éĻ¬
    -0.08
    强åĪ¶
    -0.08
    olan
    -0.08
    POSITIVE LOGITS
    åıł
    0.14
    èµ·æĿ¥
    0.14
    èµ·æĿ¥äºĨ
    0.13
    åıłåĬł
    0.11
    åľ¨ä¸Ģèµ·
    0.11
     stacking
    0.11
    æijŀ
    0.11
    èµ·ä¾Ĩ
    0.10
    èIJ½åı¶
    0.10
    (stack
    0.10
    Activations Density 0.046%

    No Known Activations