© 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. 2320
    Prev
    Next
    INDEX
    Explanations

    1

    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
    ðŁ¥ĩ
    -0.26
     Ä°stanbul
    -0.23
    檩
    -0.20
     Complex
    -0.20
    ectomy
    -0.20
    åıįèħIJåĢ¡å»ī
    -0.20
     Strait
    -0.19
    âľį
    -0.19
    Complex
    -0.19
    çŨ
    -0.19
    POSITIVE LOGITS
    orgetown
    0.26
    atego
    0.25
    èļ§
    0.25
    /Edit
    0.25
    tplib
    0.23
    [url
    0.22
    jni
    0.22
    xba
    0.21
    ·»
    0.21
    xae
    0.21
    Activations Density 0.021%

    No Known Activations