© 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. 55483
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and code explanations

    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
    æīĢæľī人
    -0.09
    ä¼Ĭå§ĭ
    -0.09
    äºİæĺ¯æĪij
    -0.08
    åĮ£
    -0.08
    èĭ¥å¹²
    -0.08
    é¼ĭ
    -0.08
    åįģåĽĽäºĶ
    -0.08
     lẽ
    -0.08
    åľ¨æĪijçļĦ
    -0.08
    å°ıå¾®
    -0.08
    POSITIVE LOGITS
     erotik
    0.10
     Eck
    0.10
    _COMPLEX
    0.09
     köln
    0.09
    ritt
    0.09
     erotisk
    0.09
     Geile
    0.08
    veloper
    0.08
    MOTE
    0.08
    reat
    0.08
    Activations Density 0.578%

    No Known Activations