© 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. 1358
    Prev
    Next
    INDEX
    Explanations

    fear, ending, enough, never, ever, Nevertheless

    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
     currently
    -0.10
     constantly
    -0.10
    ãĥ£
    -0.10
     presently
    -0.10
     initially
    -0.09
    psc
    -0.09
    apk
    -0.08
     frequently
    -0.08
     already
    -0.08
    ollen
    -0.08
    POSITIVE LOGITS
    -ending
    0.17
    theless
    0.15
    -ever
    0.14
    green
    0.14
    -present
    0.12
    more
    0.12
    rr
    0.12
    ending
    0.11
    where
    0.11
    mind
    0.11
    Activations Density 0.717%

    No Known Activations