© 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. 1667
    Prev
    Next
    INDEX
    Explanations

    achieved by

    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
     whence
    -0.11
    AndPassword
    -0.10
    orgt
    -0.10
     ÑĩÑĤобÑĭ
    -0.10
    -mediated
    -0.09
     afin
    -0.09
     seh
    -0.09
    -Based
    -0.09
     generates
    -0.09
    -based
    -0.09
    POSITIVE LOGITS
     through
    0.15
     via
    0.15
     by
    0.13
    via
    0.13
     THROUGH
    0.11
    through
    0.11
     using
    0.11
    _by
    0.11
     Through
    0.10
    éĢļè¿ĩ
    0.10
    Activations Density 3.981%

    No Known Activations