© 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. 5151
    Prev
    Next
    INDEX
    Explanations

    absurd, surreal,Kafka, Heller

    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
    çĭ¬
    -0.09
     remin
    -0.09
     Goldman
    -0.09
    çį¨
    -0.08
    Interactive
    -0.08
    å¿ł
    -0.08
     инÑĤеÑĢеÑģ
    -0.08
    鸢
    -0.08
    漪
    -0.08
     repr
    -0.08
    POSITIVE LOGITS
    èįĴ
    0.17
    åĸľåī§
    0.11
    æĥ³è±¡åĬĽ
    0.11
     surreal
    0.11
     absurd
    0.10
    çİ°å®ŀä¸Ń
    0.10
    éĢ»
    0.10
    å½ĵå±Ģ
    0.10
    讽åĪº
    0.10
    å¤¸å¼ł
    0.10
    Activations Density 0.072%

    No Known Activations