© 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. 2296
    Prev
    Next
    INDEX
    Explanations

    biological cell counts

    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
    -fw
    -0.26
    ëIJ¬
    -0.24
    leanor
    -0.24
     dikke
    -0.24
    -toggler
    -0.23
    /vendors
    -0.23
    alborg
    -0.23
     honda
    -0.22
    /Register
    -0.21
     libertin
    -0.21
    POSITIVE LOGITS
    strcasecmp
    0.26
    BootApplication
    0.23
    strstr
    0.21
    .getCurrentUser
    0.21
                        ↵                    ↵
    0.20
    MatrixXd
    0.20
    ansi
    0.20
    yx
    0.19
    Refreshing
    0.19
     تراÙħب
    0.19
    Activations Density 0.028%

    No Known Activations