© 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. 55638
    Prev
    Next
    INDEX
    Explanations

    city names

    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
    shire
    -0.10
    eres
    -0.10
    ä¸Ģå¼Ģå§ĭå°±
    -0.10
    åĬłåĽº
    -0.10
    keit
    -0.09
    ви
    -0.09
    aspers
    -0.09
    eware
    -0.09
    åĢĶ
    -0.09
    åħ³ä¹İ
    -0.09
    POSITIVE LOGITS
    iful
    0.10
    دÙĩ
    0.10
    ille
    0.09
    acha
    0.09
    izard
    0.09
    fully
    0.09
    ãģĤãĤĬ
    0.09
    illez
    0.09
    amac
    0.09
    idel
    0.08
    Activations Density 0.065%

    No Known Activations