© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1353
    Prev
    Next
    INDEX
    Explanations

    court cases

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    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
    .MaximizeBox
    -0.22
    udeau
    -0.22
    çı£
    -0.21
    ä¸Ĭå²Ĺ
    -0.20
    大éħĴåºĹ
    -0.19
    ὺ
    -0.19
     "";
    -0.19
    å²Ĺ
    -0.19
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.19
    æĹ»
    -0.18
    POSITIVE LOGITS
     prostit
    0.24
     Cases
    0.23
    éta
    0.23
    .nativeElement
    0.23
    游æĪı代
    0.22
    ä½ıæĪ¿åħ¬ç§¯
    0.22
     Parenthood
    0.22
     ])->
    0.21
     cases
    0.21
     striker
    0.21
    Activations Density 0.811%

    No Known Activations