© 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. 2712
    Prev
    Next
    INDEX
    Explanations

    or combinations

    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
     Fam
    -0.10
    adb
    -0.10
    :↵↵↵↵
    -0.09
    yum
    -0.09
     decency
    -0.09
    pit
    -0.09
     centr
    -0.09
    lyph
    -0.08
    stripe
    -0.08
    Better
    -0.08
    POSITIVE LOGITS
     completely
    0.13
     combinations
    0.12
     mixed
    0.12
     entirely
    0.11
     Combination
    0.11
     totally
    0.11
     outright
    0.11
     None
    0.11
     none
    0.10
     combination
    0.10
    Activations Density 0.460%

    No Known Activations