© 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. 38328
    Prev
    Next
    INDEX
    Explanations

    Rudolph, Rudy, Rudiments, Ruderman, Rudersdal

    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
    çĦ¶æĺ¯
    -0.13
    æ°¨éħ¸
    -0.11
    ingly
    -0.11
    èĦĨ
    -0.09
    uÃŃ
    -0.09
    erin
    -0.09
    æ©Ļ
    -0.09
    èµ´
    -0.09
    opic
    -0.09
    å¹Ħ
    -0.09
    POSITIVE LOGITS
    åĿļå®ŀçļĦ
    0.10
    icker
    0.09
    -fashioned
    0.09
    alian
    0.09
    duc
    0.09
    å·´å·´
    0.08
    ied
    0.08
     meanwhile
    0.08
    asant
    0.08
    è··
    0.08
    Activations Density 0.013%

    No Known Activations