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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52011
    Prev
    Next
    INDEX
    Explanations

    art and lies

    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
     fantas
    -0.10
    è¿ĩé«ĺ
    -0.09
    åıijæĺİä¸ĵåĪ©
    -0.09
    åıłåĬł
    -0.09
    ä¸Ģ个éĹ®é¢ĺ
    -0.09
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.09
    亲å¯Ĩ
    -0.08
    ungan
    -0.08
    ÑĢаÑģÑĤ
    -0.08
    ä¸įå®Į
    -0.08
    POSITIVE LOGITS
     arts
    0.12
    èīºæľ¯
    0.12
    /art
    0.11
     Arts
    0.10
    åĪĽä½ľ
    0.10
    arts
    0.10
     MOM
    0.09
     art
    0.09
    ìĺĪìĪł
    0.09
    å½¢å¼ı
    0.09
    Activations Density 0.092%

    No Known Activations