© 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. 54401
    Prev
    Next
    INDEX
    Explanations

    place names ending in ville

    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
    пÑĢÑı
    -0.10
     threaded
    -0.09
    åIJĥå¾Ĺ
    -0.08
    ãģĹãģ¾ãģĦ
    -0.08
    zej
    -0.08
    Earn
    -0.08
    ISTER
    -0.08
     Bison
    -0.08
     natur
    -0.08
    _deps
    -0.08
    POSITIVE LOGITS
    æīĵåĬ¨
    0.09
    æĺŁçº§
    0.09
    çĺĢ
    0.09
    agli
    0.09
    个人è§ĤçĤ¹
    0.09
    æį»
    0.09
    æĦŁåĬ¨
    0.08
    代表æĢ§
    0.08
    older
    0.08
    hol
    0.08
    Activations Density 0.025%

    No Known Activations