© 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. 31104
    Prev
    Next
    INDEX
    Explanations

    lenses and optics

    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
    åīª
    -0.09
    -animate
    -0.09
    åŁĭ
    -0.09
    çĦ¯
    -0.09
    æµĩ
    -0.08
    éĻª
    -0.08
    æĶ¥
    -0.08
    ç«ĻçĿĢ
    -0.08
    éĢļéģĵ
    -0.08
    åŁł
    -0.08
    POSITIVE LOGITS
    åħīåѦ
    0.15
     lenses
    0.15
     lens
    0.15
    çľ¼éķľ
    0.14
    è¿ijè§Ĩ
    0.14
    æĬĺå°Ħ
    0.13
    éķľå¤´
    0.13
     Lens
    0.13
    Lens
    0.12
     optics
    0.11
    Activations Density 0.119%

    No Known Activations