© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9731
    Prev
    Next
    INDEX
    Explanations

    place names ending in wood, dale, ridge, view

    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
    æĢ§å¼º
    -0.09
    çķĮ
    -0.09
    çŁ³
    -0.09
     Jeb
    -0.08
    æ°ª
    -0.08
    çĹĽçĤ¹
    -0.08
    管å±Ģ
    -0.08
    mate
    -0.08
    isson
    -0.08
     Matthias
    -0.08
    POSITIVE LOGITS
    éĻ¤å¤ķ
    0.10
    RAR
    0.10
    ÑĤики
    0.10
    ä¿¡èªī
    0.10
    homes
    0.10
    å°ıåĮº
    0.09
    éĤ»éĩĮ
    0.09
    é¤IJåħ·
    0.09
    åģİ
    0.09
    享çĶ¨
    0.09
    Activations Density 0.094%

    No Known Activations