© 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. 27704
    Prev
    Next
    INDEX
    Explanations

    military bases and regions

    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
    å±ħ家
    -0.10
    å·¾
    -0.09
    ounc
    -0.09
    å¼Ħ
    -0.08
    æľĿçĿĢ
    -0.08
    çݯèĬĤ
    -0.08
    ä¿¡çĶ¨
    -0.08
    èŀįåĮĸ
    -0.08
    æ°Ķæ°Ľ
    -0.08
    å¤ĸåĩº
    -0.08
    POSITIVE LOGITS
    é©»
    0.13
    é§IJ
    0.12
    presence
    0.11
     presence
    0.11
    派驻
    0.11
    ĶĦ
    0.10
     Presence
    0.10
    驼
    0.09
     presença
    0.09
    èĩªæѤ
    0.09
    Activations Density 0.057%

    No Known Activations