© 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. 56638
    Prev
    Next
    INDEX
    Explanations

    copyright notices or disclaimers

    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
    ymm
    -0.12
    (Sub
    -0.10
    onn
    -0.10
     expans
    -0.10
    -exp
    -0.10
    nant
    -0.09
     alte
    -0.09
    /Branch
    -0.09
    -expand
    -0.09
    onds
    -0.09
    POSITIVE LOGITS
     whose
    0.09
     marrow
    0.08
    vette
    0.07
     Hal
    0.07
    ç±
    0.07
    ju
    0.07
     ones
    0.07
    .meta
    0.07
     Ranger
    0.07
    whose
    0.07
    Activations Density 0.376%

    No Known Activations