© 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. 39385
    Prev
    Next
    INDEX
    Explanations

    forms of "to be"

    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
    ulls
    -0.09
    çŀij
    -0.09
    æű
    -0.09
    iqu
    -0.09
    åĵĻ
    -0.08
    avs
    -0.08
    liers
    -0.08
    èĮħ
    -0.08
    amas
    -0.08
     اÙĦعب
    -0.08
    POSITIVE LOGITS
    åľ¨äºİ
    0.13
    èİ«è¿ĩäºİ
    0.12
    éĤ£å°±æĺ¯
    0.12
    å°±åľ¨äºİ
    0.11
    çļĦéĩįçĤ¹
    0.11
    éĩįä¸Ńä¹ĭéĩį
    0.10
    å±İ
    0.10
    çļĦåħ³æ³¨
    0.10
    ãn
    0.10
    æł¸åĩĨ
    0.09
    Activations Density 0.202%

    No Known Activations