© 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. 10145
    Prev
    Next
    INDEX
    Explanations

    word endings in 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
    urs
    -0.09
    åĩºè·¯
    -0.09
    itol
    -0.09
    å·¡è§Ĩ
    -0.09
     kald
    -0.08
    ä¸ĸ人
    -0.08
    请éĢīæĭ©
    -0.08
    оÑģÑĤÑĮÑİ
    -0.08
    ä¸ī代
    -0.08
     Sar
    -0.08
    POSITIVE LOGITS
    aira
    0.10
     Tro
    0.10
    æı´
    0.09
    å©Ĩ
    0.09
    æģ¬
    0.08
    entions
    0.08
    ennon
    0.08
    åĢľ
    0.08
     tro
    0.08
    aries
    0.08
    Activations Density 0.004%

    No Known Activations