© 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. 47821
    Prev
    Next
    INDEX
    Explanations

    titles and noble ranks

    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
    衾
    -0.09
    dden
    -0.08
    yaw
    -0.08
    ordination
    -0.08
    íĮ©
    -0.08
    æĿī
    -0.08
    itical
    -0.08
    å·Ŀ
    -0.08
     thuáºŃt
    -0.08
     Fellow
    -0.08
    POSITIVE LOGITS
    asm
    0.10
    çĢĽ
    0.09
    å½¼
    0.09
    ä¸Ģ线
    0.09
    åĽ½åĨħå¸Ĥåľº
    0.09
    åĪĨè¡Į
    0.09
    æŁľåı°
    0.08
    éĢĻ裡
    0.08
    ç£ĭåķĨ
    0.08
    æŁIJç§į
    0.08
    Activations Density 0.066%

    No Known Activations