© 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. 10292
    Prev
    Next
    INDEX
    Explanations

    playing with toys or around

    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
    ider
    -0.09
    åIJ¸
    -0.09
    æĭ¦
    -0.09
    IDER
    -0.09
     synd
    -0.08
     ÐŃÑĤ
    -0.08
    ãĥĥãĤ¯ãĤ¹
    -0.08
    åIJ¬å¾Ĺ
    -0.08
     videot
    -0.08
     Eig
    -0.08
    POSITIVE LOGITS
    çİ©
    0.16
    çİ©èĢį
    0.16
    çİ©åħ·
    0.16
     toys
    0.14
     toy
    0.13
     playground
    0.12
     Toys
    0.12
    好çİ©
    0.12
    ç¿
    0.11
    toy
    0.11
    Activations Density 0.081%

    No Known Activations