© 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. 6654
    Prev
    Next
    INDEX
    Explanations

    machines and apparatus suffixes

    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
    åĪĽå»ºå·¥ä½ľ
    -0.10
    åĻ¨ä»¶
    -0.09
    oen
    -0.09
    åģļä¸Ģ个
    -0.09
    éĵ³
    -0.08
    åľ¨éĩĮéĿ¢
    -0.08
    ervoir
    -0.08
    éķ³
    -0.08
    Fmt
    -0.08
    åIJ¬çĿĢ
    -0.08
    POSITIVE LOGITS
    æľº
    0.12
    æ©Ł
    0.10
    强大
    0.10
    仪
    0.10
    æµģæ°´
    0.09
    ä¸Ģä½ĵ
    0.09
     machine
    0.09
    综åIJĪä½ĵ
    0.09
    ä¸Ģåı°
    0.09
    ÑĮÑİ
    0.08
    Activations Density 0.303%

    No Known Activations