© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56267
    Prev
    Next
    INDEX
    Explanations

    tens digit of a number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hof
    -0.10
    oba
    -0.10
     Ville
    -0.10
    kad
    -0.09
    ostringstream
    -0.09
     Square
    -0.09
    egen
    -0.09
    kus
    -0.09
     sag
    -0.09
     greens
    -0.09
    POSITIVE LOGITS
     subtype
    0.10
    ately
    0.08
    -parser
    0.08
    imeo
    0.08
    失
    0.07
     Rol
    0.07
    ata
    0.07
     setC
    0.07
     tender
    0.07
    amer
    0.07
    Activations Density 0.001%

    No Known Activations