© 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. 27161
    Prev
    Next
    INDEX
    Explanations

    narrative elements character plot motivation

    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
    antha
    -0.10
    æĬĬèĩªå·±çļĦ
    -0.10
    躺çĿĢ
    -0.10
    æĬĬèĩªå·±
    -0.09
    ÐIJÐŀ
    -0.09
    é¢ĩæľī
    -0.09
    躺
    -0.09
    IPA
    -0.08
    ounder
    -0.08
     Hund
    -0.08
    POSITIVE LOGITS
    主人åħ¬
    0.11
    åıįèħIJåĢ¡å»ī
    0.10
    çĪ±æĥħ
    0.10
    è¿Ń
    0.09
    åĨ²çªģ
    0.09
    å¾®è§Ĥ
    0.09
    æģĭçĪ±
    0.09
    çļĦçĪ±æĥħ
    0.09
     characters
    0.09
    èĻIJ
    0.09
    Activations Density 0.093%

    No Known Activations