© 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. 61213
    Prev
    Next
    INDEX
    Explanations

    starting out

    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
     being
    -0.11
    åĤ¥
    -0.09
    樯
    -0.08
    åĨĻçĿĢ
    -0.08
    å¼ĵ
    -0.08
    æĥ³çĿĢ
    -0.08
    nt
    -0.08
    cheid
    -0.08
    梳
    -0.08
     peg
    -0.08
    POSITIVE LOGITS
    è¦ģåĬłå¼º
    0.09
    çļĦåį°è±¡
    0.09
    èĤĮèĤ¤
    0.09
    éŃ
    0.09
    ÑģÑĤвоваÑĤÑĮ
    0.09
    è½½ä½ĵ
    0.09
    è¦ģ说
    0.09
    è¦ģåĿļæĮģ
    0.08
    éħ£
    0.08
    éĥ¨åĪĨåĨħ容
    0.08
    Activations Density 0.029%

    No Known Activations