© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 54915
    Prev
    Next
    INDEX
    Explanations

    private, confidential, or sensitive information

    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
     Slice
    -0.12
    ÄĻ
    -0.10
    heads
    -0.10
     Complexity
    -0.10
    enie
    -0.10
    hab
    -0.09
    elper
    -0.09
    head
    -0.09
     wholes
    -0.09
     Unused
    -0.09
    POSITIVE LOGITS
    idar
    0.08
    tera
    0.07
     consequential
    0.07
     elig
    0.07
     shouldn
    0.07
     Dak
    0.07
    innamon
    0.07
    pat
    0.07
     pat
    0.06
     ACT
    0.06
    Activations Density 0.050%

    No Known Activations