© 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. 19433
    Prev
    Next
    INDEX
    Explanations

    financial analysis charts

    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
    _different
    -0.09
    orget
    -0.09
     conv
    -0.09
    åıĹçĽĬ
    -0.09
     íļ
    -0.09
    addresses
    -0.09
    æĿĻ
    -0.09
    vic
    -0.09
    chie
    -0.08
    èĮħ
    -0.08
    POSITIVE LOGITS
    å¤ļä½Ļ
    0.08
    4
    0.08
    æĺ¯ä»Ģä¹Īåij¢
    0.08
    8
    0.08
    ck
    0.08
    2
    0.08
    éĩijä»·
    0.08
    .Toolkit
    0.08
    åĬŀäºĭå¤Ħ
    0.08
    åŃ£èĬĤ
    0.07
    Activations Density 0.067%

    No Known Activations