© 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. 6193
    Prev
    Next
    INDEX
    Explanations

    vascular space invasion, clinicopathological

    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
    娱
    -0.10
    èĤ¤
    -0.10
    æİĴéĻ¤
    -0.09
    飽
    -0.08
    æŶæŶ
    -0.08
    ighted
    -0.08
    çŁ³èĨı
    -0.08
    amina
    -0.08
    oured
    -0.08
    è¦ĨçĽĸ
    -0.08
    POSITIVE LOGITS
    exion
    0.11
    æī©æķ£
    0.10
     Nab
    0.09
    keit
    0.09
    Gre
    0.09
     saddle
    0.09
    级åĪ«
    0.09
    äºļ太
    0.09
    Nib
    0.08
    ÑıÑģ
    0.08
    Activations Density 0.641%

    No Known Activations