© 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. 49745
    Prev
    Next
    INDEX
    Explanations

    short and long term

    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
    è¡ĮæĶ¿éĥ¨éŨ
    -0.10
    ä¸Ģ个æĸ°çļĦ
    -0.09
    aden
    -0.09
    ستر
    -0.09
    æĹ»
    -0.09
    æĽĻ
    -0.09
    ocket
    -0.09
    ierce
    -0.08
    èĿ¶
    -0.08
    èѦæĥķ
    -0.08
    POSITIVE LOGITS
    éķ¿è¿ľ
    0.21
    éķ¿æľŁ
    0.18
    çŁŃæľŁ
    0.17
    éķ¿ä¹ħ
    0.16
    éķ·æľŁ
    0.15
    éķ¿æķĪ
    0.14
    çŁŃæľŁåĨħ
    0.14
     долг
    0.13
    æĮģä¹ħ
    0.13
     long
    0.13
    Activations Density 0.075%

    No Known Activations