© 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. 38214
    Prev
    Next
    INDEX
    Explanations

    villa, home, house, lodge

    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
    æĪ¿
    -0.10
     hall
    -0.09
    .strict
    -0.08
    liable
    -0.08
    åİĤæĪ¿
    -0.08
     Hall
    -0.08
    è¡Įç¨ĭ
    -0.08
    æħİéĩį
    -0.08
     Acts
    -0.07
    mond
    -0.07
    POSITIVE LOGITS
    ä½łä»¥ä¸º
    0.10
    èĩ
    0.10
    ä½łåºĶ该
    0.09
    PUR
    0.09
    å´
    0.09
    åį®
    0.09
    ç°
    0.09
    è¦ģåѦä¼ļ
    0.09
    iners
    0.09
    åĬŀäºĭ
    0.09
    Activations Density 0.040%

    No Known Activations