© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61998
    Prev
    Next
    INDEX
    Explanations

    immunohistochemical staining expression

    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
    æĤ£çĹħ
    -0.10
    åħ¥èĤ¡
    -0.10
    ensis
    -0.09
    ä½ĵæ£Ģ
    -0.08
     Ñģог
    -0.08
     carved
    -0.08
    ouve
    -0.08
    踢
    -0.08
     ort
    -0.08
     spons
    -0.08
    POSITIVE LOGITS
    çŃı
    0.10
    çĭŃ
    0.09
    ç¼Ŀ
    0.09
    å¯Į
    0.09
    汩
    0.09
    èĮĥ
    0.09
    饰åĵģ
    0.09
    æŀ¶åŃIJ
    0.09
    åļ¼
    0.08
    ä¹ı
    0.08
    Activations Density 0.562%

    No Known Activations