© 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. 6420
    Prev
    Next
    INDEX
    Explanations

    anesthetized

    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
    ENTIC
    -0.11
    主è¦ģé¢Ĩ导
    -0.10
    äºĽ
    -0.09
    å·¥ä½ľçļĦ
    -0.09
    åĪ°æĿ¥
    -0.09
    akk
    -0.09
    碲
    -0.09
    æ°¨éħ¸
    -0.09
    好å¤Ħ
    -0.08
    æŶåĢĻ
    -0.08
    POSITIVE LOGITS
    à¹Į
    0.15
    aurus
    0.11
    ally
    0.10
    rog
    0.10
    ingly
    0.09
    иÑĤелÑĮно
    0.08
    stüt
    0.08
    1
    0.08
    mes
    0.08
    3
    0.08
    Activations Density 0.493%

    No Known Activations