© 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. 603
    Prev
    Next
    INDEX
    Explanations

    articles with countable nouns

    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
     mere
    -0.09
     woes
    -0.09
     afore
    -0.08
    quarter
    -0.08
     premises
    -0.07
     troubled
    -0.07
     terse
    -0.07
     quarter
    -0.07
     headaches
    -0.07
    aku
    -0.07
    POSITIVE LOGITS
     plenty
    0.16
     overlap
    0.14
     reason
    0.14
     difference
    0.14
     no
    0.13
     disagreement
    0.13
     room
    0.12
     overlaps
    0.12
     way
    0.12
     shortage
    0.12
    Activations Density 0.909%

    No Known Activations