© 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. 1928
    Prev
    Next
    INDEX
    Explanations

    paper references

    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
     strugg
    -0.24
    游æĪıæĵįä½ľ
    -0.24
     puss
    -0.23
     dirent
    -0.21
     (_)
    -0.21
     ifndef
    -0.20
    isse
    -0.20
     Tops
    -0.19
    abcdefghijkl
    -0.19
     buurt
    -0.19
    POSITIVE LOGITS
    è§ģ
    0.33
    éĻĦ
    0.29
     Table
    0.28
     Figure
    0.28
     figure
    0.27
    详è§ģ
    0.27
     see
    0.25
    Append
    0.24
    }'",
    0.24
     Fig
    0.23
    Activations Density 0.146%

    No Known Activations