© 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. 56899
    Prev
    Next
    INDEX
    Explanations

    .com / framework / if

    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
    ppo
    -0.10
     muse
    -0.10
    aha
    -0.10
    ose
    -0.10
     $_[
    -0.10
     shed
    -0.10
     sinking
    -0.09
     bais
    -0.09
    ces
    -0.09
     Ñģлед
    -0.09
    POSITIVE LOGITS
    ullo
    0.07
    Hex
    0.07
     Ev
    0.07
     branch
    0.07
     Harbor
    0.07
     Ved
    0.07
    .getvalue
    0.06
     stab
    0.06
     prim
    0.06
    igar
    0.06
    Activations Density 0.002%

    No Known Activations