© 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. 31886
    Prev
    Next
    INDEX
    Explanations

    fate and destiny

    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
    éĥ½è¯´
    -0.10
    artz
    -0.09
    abbo
    -0.09
    ãĤīãģĽ
    -0.09
    æľīæīĢ
    -0.09
    mare
    -0.09
    çĿ¥
    -0.09
    (generator
    -0.09
    èĺijèıĩ
    -0.08
    å¾Ģå¤ĸ
    -0.08
    POSITIVE LOGITS
    åij½è¿IJ
    0.24
     fate
    0.22
    çļĦåij½è¿IJ
    0.21
    ç»ĵå±Ģ
    0.15
     Fate
    0.14
     destiny
    0.13
    è¦Ĩ
    0.13
     destino
    0.12
    ç¥ļ
    0.10
    å¤Ħå¢ĥ
    0.10
    Activations Density 0.016%

    No Known Activations