© 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. 49906
    Prev
    Next
    INDEX
    Explanations

    interferometer technology

    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
    åĸı
    -0.09
    ä¸įçĶĺ
    -0.09
    æĸ§
    -0.09
    ä¹łä¿Ĺ
    -0.09
     пÑĢакÑĤиÑĩ
    -0.09
    bus
    -0.09
    ä¸į失
    -0.08
    Ñįн
    -0.08
     поÑģл
    -0.08
    öt
    -0.08
    POSITIVE LOGITS
    è¾ĥéķ¿
    0.10
     Bau
    0.09
    åĽŀåºĶ
    0.09
    é»ĺé»ĺåľ°
    0.09
    ovsky
    0.08
    Bright
    0.08
    åħ³éĹŃ
    0.08
    ometer
    0.08
    æļĹ
    0.08
    IRR
    0.08
    Activations Density 0.054%

    No Known Activations