© 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. 56171
    Prev
    Next
    INDEX
    Explanations

    levels or comparisons

    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
     reverse
    -0.11
    -counter
    -0.10
     Counter
    -0.10
     Reverse
    -0.10
     reversed
    -0.10
    reverse
    -0.09
     Temp
    -0.09
     reversing
    -0.09
     revers
    -0.09
     reversal
    -0.09
    POSITIVE LOGITS
     Hamm
    0.09
    als
    0.09
    aylor
    0.09
     Verm
    0.09
     singles
    0.09
     squ
    0.09
    izard
    0.08
    ocr
    0.08
    OI
    0.08
     vero
    0.08
    Activations Density 0.064%

    No Known Activations