© 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. 23444
    Prev
    Next
    INDEX
    Explanations

    shipping times and availability

    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
     Kapoor
    -0.09
    çĭ±
    -0.09
    èĽĻ
    -0.09
    å¹²åĩĢ
    -0.09
    çĶ¨æ°´
    -0.08
    IgnoreCase
    -0.08
    æ´Ļ
    -0.08
    resh
    -0.08
    å²©çŁ³
    -0.08
    çĪ¨
    -0.08
    POSITIVE LOGITS
    upy
    0.09
    å¨ĺ
    0.09
    amil
    0.09
    obook
    0.09
    ectl
    0.09
    cea
    0.08
    림
    0.08
    ClientRect
    0.08
    å¼¹æĢ§
    0.08
     mát
    0.08
    Activations Density 0.156%

    No Known Activations