© 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. 48155
    Prev
    Next
    INDEX
    Explanations

    Japan, specific places

    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
    ä½İä¼°
    -0.09
    岸
    -0.09
    fast
    -0.09
    ines
    -0.09
    åĬĽäºī
    -0.08
     пÑĥнк
    -0.08
    ROM
    -0.08
     Wet
    -0.08
     wet
    -0.08
     ÙĨÙģسÙĩا
    -0.08
    POSITIVE LOGITS
    _NR
    0.12
    nr
    0.10
     NR
    0.10
    reau
    0.09
    otech
    0.09
    heim
    0.09
    éħĹ
    0.09
    hest
    0.09
    å°Ħ
    0.09
    oola
    0.09
    Activations Density 0.003%

    No Known Activations