© 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. 54778
    Prev
    Next
    INDEX
    Explanations

    depression, recession, or sliding into trouble

    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
    çģ«çĪĨ
    -0.09
    æĸŃ
    -0.09
    nth
    -0.09
    åŃº
    -0.08
    ç«ŀ
    -0.08
     intptr
    -0.08
     возможноÑģÑĤи
    -0.08
    è¯ķ
    -0.08
    ymous
    -0.08
    æĻļéĹ´
    -0.08
    POSITIVE LOGITS
    éĻ·åħ¥
    0.13
    æ·±æ¸Ĭ
    0.12
    éĻ·åħ¥äºĨ
    0.12
     depression
    0.12
    è¡°
    0.11
    å¤įèĭı
    0.11
    严éĩįçļĦ
    0.11
    è¡°éĢĢ
    0.11
    åĽ°å¢ĥ
    0.10
    esy
    0.10
    Activations Density 0.056%

    No Known Activations