© 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. 1103
    Prev
    Next
    INDEX
    Explanations

    positive praise for people

    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
     vaguely
    -0.12
     somewhat
    -0.11
     infamous
    -0.11
     presumably
    -0.11
    -ish
    -0.11
     roughly
    -0.11
     supposedly
    -0.10
     murky
    -0.10
     attempts
    -0.10
     abruptly
    -0.10
    POSITIVE LOGITS
     excellent
    0.18
     wonderful
    0.16
     outstanding
    0.16
     invaluable
    0.15
     truly
    0.15
     deserved
    0.14
     amazing
    0.14
     great
    0.14
     terrific
    0.14
     deserves
    0.14
    Activations Density 2.416%

    No Known Activations