© 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. 32825
    Prev
    Next
    INDEX
    Explanations

    disaster scenarios

    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
    _fatal
    -0.09
    ç¬
    -0.09
     bare
    -0.08
    è¡£æľį
    -0.08
    .bz
    -0.08
    ç¼Ĺ
    -0.08
    ãĥŃãĥ³
    -0.08
    è¿ĽäºĨ
    -0.08
    æį¢åıĸ
    -0.08
    7
    -0.08
    POSITIVE LOGITS
    æĪĸåħ¶ä»ĸ
    0.09
    蹩
    0.09
    æĪĸèĢħåħ¶ä»ĸ
    0.09
    éģĹ
    0.09
    åĭĭ
    0.09
    æģķ
    0.09
     Leban
    0.08
    ä¸įå¼Ģ
    0.08
     Svens
    0.08
     невоз
    0.08
    Activations Density 0.029%

    No Known Activations