© 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. 63789
    Prev
    Next
    INDEX
    Explanations

    names ending in -berg

    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
    ä¸įèĥ½åĨį
    -0.10
    itional
    -0.10
    æĥķ
    -0.10
    enance
    -0.09
    ä½ķå¿ħ
    -0.09
    ı
    -0.09
    _elim
    -0.09
    unce
    -0.09
    æī¿å¾·
    -0.09
    leh
    -0.09
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.10
    ãģĩ
    0.10
    ally
    0.09
    ers
    0.09
    ç¿ķ
    0.09
    thal
    0.09
     fact
    0.09
    sex
    0.08
    shire
    0.08
    t
    0.08
    Activations Density 0.010%

    No Known Activations