© 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. 31436
    Prev
    Next
    INDEX
    Explanations

    times of hardship

    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
    å¿ĥåĬ¨
    -0.11
     Pale
    -0.09
    å¸Ī
    -0.09
    è¿ŁåĪ°
    -0.08
    rompt
    -0.08
     scoop
    -0.08
    ä¸Ģå¹´ä¸Ģ度
    -0.08
    nen
    -0.08
    woke
    -0.08
     Lump
    -0.08
    POSITIVE LOGITS
    åĽ°éļ¾
    0.14
    åħ³éĶ®æŶåĪ»
    0.14
    èī°éļ¾
    0.13
    éļ¾åħ³
    0.12
    åĽ°éĽ£
    0.12
    çļĦæĹ¥åŃIJ
    0.12
    æĹ¶æľŁ
    0.12
    æŶåĢĻ
    0.12
    åį±
    0.12
    åĽ°å¢ĥ
    0.12
    Activations Density 0.062%

    No Known Activations