© 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. 2117
    Prev
    Next
    INDEX
    Explanations

    biology

    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
    ("(%
    -0.23
     Ä°n
    -0.21
    对çħ§æ£ĢæŁ¥
    -0.21
    åijĬ
    -0.20
     Premiership
    -0.19
    }());↵
    -0.18
    æ¶īåıĬ
    -0.18
    FileChooser
    -0.18
    phalt
    -0.18
     cells
    -0.18
    POSITIVE LOGITS
    âĦī
    0.25
    .cz
    0.23
    -haspopup
    0.21
     IonicPage
    0.21
    åİŁåŀĭ
    0.20
    ?>>
    0.20
    glÄħd
    0.20
    CLUDING
    0.20
    stdexcept
    0.20
    å´§
    0.20
    Activations Density 0.384%

    No Known Activations