© 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. 56156
    Prev
    Next
    INDEX
    Explanations

    sitting at or around

    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
    ospace
    -0.09
    æķĪçĽĬ
    -0.09
    åħ¨è¿ĩç¨ĭ
    -0.09
    åħ¨åŁŁ
    -0.09
    ër
    -0.09
    åľ¨åĨħçļĦ
    -0.09
    çļĦ空éĹ´
    -0.09
    banana
    -0.08
    åİ»çľĭ
    -0.08
    èģ©
    -0.08
    POSITIVE LOGITS
    ä¸ĢéĿ¢
    0.09
     Gn
    0.09
    è¾¹
    0.09
    èŃ
    0.08
    宣æī¬
    0.08
    ubs
    0.08
    زاÙĨ
    0.08
     GRA
    0.08
    éĤĬ
    0.08
    çªĹ
    0.08
    Activations Density 0.025%

    No Known Activations