© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 382
    Prev
    Next
    INDEX
    Explanations

    explicit sexual content

    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
    并ä¸įæĺ¯å¾Ī
    -0.22
    åħ¶å®ĥéĹ®é¢ĺ
    -0.20
    подоб
    -0.20
     d
    -0.20
    PHPUnit
    -0.20
    ç¡IJ
    -0.19
     hmac
    -0.19
    .RadioButton
    -0.19
     Cov
    -0.19
    ÙĨعÙħ
    -0.19
    POSITIVE LOGITS
    aceut
    0.26
     Erotic
    0.26
    ialized
    0.25
     LENG
    0.25
     libertine
    0.25
    crast
    0.24
    iá»ĩn
    0.24
     Erectile
    0.23
    anship
    0.23
    (*)(
    0.23
    Activations Density 0.616%

    No Known Activations