© 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. 3044
    Prev
    Next
    INDEX
    Explanations

    tumor detection and induction

    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
    çĦ¶æĺ¯
    -0.11
    ä»Ģä¹Īåij¢
    -0.10
    ÙĦع
    -0.10
    ached
    -0.09
    oris
    -0.09
    nton
    -0.09
    еÑĢÑĮ
    -0.09
    erah
    -0.09
    iÄħ
    -0.09
    orer
    -0.09
    POSITIVE LOGITS
    ally
    0.15
    ously
    0.10
    /***/
    0.08
    ../../../
    0.08
    Ùī
    0.08
    ono
    0.08
    Â
    0.08
    åĻİ
    0.08
    ÂĢÂĻ
    0.08
    ë§ģ
    0.08
    Activations Density 0.981%

    No Known Activations