© 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. 3210
    Prev
    Next
    INDEX
    Explanations

    assistant aide

    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
    èĺħ
    -0.09
    åħ¬ä¸»
    -0.09
    念
    -0.09
    åĩºåĵģ
    -0.08
    faculty
    -0.08
    Prem
    -0.08
     FAC
    -0.08
    ichi
    -0.08
    宣
    -0.08
    æĶ¹ç¼ĸ
    -0.08
    POSITIVE LOGITS
    åĬ©æīĭ
    0.22
    åĬ©çIJĨ
    0.15
     assistants
    0.15
     assistant
    0.14
    è¾ħåĬ©
    0.14
    åįıåĬ©
    0.14
     aides
    0.13
     assistance
    0.12
     помоÑī
    0.12
    assist
    0.12
    Activations Density 0.074%

    No Known Activations