© 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. 18939
    Prev
    Next
    INDEX
    Explanations

    names of places ending in falls

    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
    umann
    -0.09
    rome
    -0.09
    ovo
    -0.09
    ãĤ´ãĥ¼ãĥ«
    -0.09
    SSION
    -0.09
    aming
    -0.08
    å¼Ģå°ģ
    -0.08
    容纳
    -0.08
    ality
    -0.08
    ëķħ
    -0.08
    POSITIVE LOGITS
    icle
    0.09
    Ñģан
    0.09
    ÑĤÑģÑı
    0.08
     Eisen
    0.08
    ported
    0.08
    meter
    0.08
    iams
    0.08
    amas
    0.08
    æµģçķħ
    0.08
    ä¹ĭ乡
    0.08
    Activations Density 0.007%

    No Known Activations