© 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. 1260
    Prev
    Next
    INDEX
    Explanations

    be followed by state or outcome

    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
     being
    -0.17
     Being
    -0.15
    being
    -0.13
    Being
    -0.13
     not
    -0.12
    not
    -0.12
     NOT
    -0.12
     supposedly
    -0.11
     never
    -0.11
     usually
    -0.11
    POSITIVE LOGITS
    COME
    0.21
    friend
    0.21
     able
    0.20
    fall
    0.16
    stride
    0.16
    gets
    0.15
    get
    0.15
    acons
    0.15
    have
    0.14
    que
    0.14
    Activations Density 0.797%

    No Known Activations