© 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. 35117
    Prev
    Next
    INDEX
    Explanations

    concepts of deception and fabrication

    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
    æŁ³
    -0.11
    aty
    -0.09
    å·¥ç¨ĭè´¨éĩı
    -0.09
    æŃ£ä¹ī
    -0.09
    éªĬ
    -0.09
    åıĭæĥħéĵ¾æİ¥
    -0.09
    ÙĤÙĩ
    -0.09
    .dev
    -0.08
    æ¶Īæŀģ
    -0.08
    asty
    -0.08
    POSITIVE LOGITS
    æĦŁåĬ¨
    0.10
     crisis
    0.09
    åį±æľº
    0.09
    AndView
    0.09
    说èĩªå·±
    0.09
    åĬ¿
    0.08
    çĹķ
    0.08
    éģŃ
    0.08
     Crisis
    0.08
    çħŀ
    0.08
    Activations Density 0.024%

    No Known Activations