© 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. 50244
    Prev
    Next
    INDEX
    Explanations

    predator interaction

    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
     оÑĤлиÑĩа
    -0.10
    à¹Ħ
    -0.09
    éĨļ
    -0.08
    âĹ»
    -0.08
     Engl
    -0.08
    客家
    -0.08
    éĽĨ
    -0.08
    WithOptions
    -0.08
    amo
    -0.08
    è¡£
    -0.08
    POSITIVE LOGITS
    çĶ¨éĩı
    0.11
    æ·ĸ
    0.10
    åħ¬å¹³
    0.10
    åľ¨åIJĮä¸Ģ
    0.10
    æİĤ
    0.09
    åģĩè£ħ
    0.09
    ä¸įäºĪ
    0.09
    ä¸Ģ次æĢ§
    0.09
    å¹´ä¹ĭ
    0.09
    æĬĬè¿ĻäºĽ
    0.09
    Activations Density 0.062%

    No Known Activations