© 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. 9694
    Prev
    Next
    INDEX
    Explanations

    kids and children

    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
    ä»Ģä¹Īåij¢
    -0.10
    éĢį
    -0.09
    è¥Ł
    -0.09
    åį¡éĢļ
    -0.09
    kees
    -0.08
    udas
    -0.08
     Ñģозда
    -0.08
    ä¿Ŀåį«
    -0.08
    setCurrent
    -0.08
    æĬ»
    -0.08
    POSITIVE LOGITS
    iec
    0.09
    ä¸įä»ħåı¯ä»¥
    0.08
    na
    0.08
    å°¸
    0.08
    ë¦Ħ
    0.08
    ses
    0.08
     Bike
    0.08
    ÑĢоÑģÑĤ
    0.08
    -boy
    0.08
     libero
    0.08
    Activations Density 0.030%

    No Known Activations