© 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. 29529
    Prev
    Next
    INDEX
    Explanations

    ranked AAA rated Bank

    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
    owie
    -0.08
    uchs
    -0.08
    etch
    -0.08
    bour
    -0.08
    ETCH
    -0.08
    бÑĥÑĢ
    -0.08
    饵
    -0.08
    (selector
    -0.08
    amble
    -0.08
    ength
    -0.08
    POSITIVE LOGITS
    è¯Ħ级
    0.17
    è¯Ħ为
    0.14
    è¯ĦåĪĨ
    0.11
     rating
    0.11
    è¯Ħå®ļ
    0.10
    é»Ħæĺı
    0.10
     ratings
    0.10
    çŃī级
    0.10
    åݻ买
    0.10
    åĦ¿ç§ij
    0.10
    Activations Density 0.043%

    No Known Activations