© 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. 61372
    Prev
    Next
    INDEX
    Explanations

    American Samoa or territories

    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
    强èĢħ
    -0.11
    å¼ĢçĿĢ
    -0.11
     deduction
    -0.10
    éĺ²çĽĹ
    -0.10
    é¢ľåĢ¼
    -0.09
    纸质
    -0.09
    å°±è¿ij
    -0.09
    éĦī
    -0.09
     ded
    -0.09
    éªĪ
    -0.09
    POSITIVE LOGITS
     territories
    0.11
    mach
    0.09
    å¢ĥ
    0.09
    æݼ
    0.09
     territory
    0.09
    éªħ
    0.09
    Flip
    0.09
    éĻĦå±ŀ
    0.09
     flips
    0.08
    éĻĦ
    0.08
    Activations Density 0.159%

    No Known Activations