© 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. 3367
    Prev
    Next
    INDEX
    Explanations

    titles and roles

    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
    oster
    -0.11
     */č↵č↵č↵
    -0.11
    ende
    -0.10
    <"
    -0.10
    rok
    -0.10
    )this
    -0.10
     ]č↵
    -0.09
     rop
    -0.09
     ceux
    -0.09
     quienes
    -0.09
    POSITIVE LOGITS
    ,
    0.13
     destination
    0.08
     hon
    0.07
    cc
    0.07
    emat
    0.07
     destinations
    0.07
     Voy
    0.07
    —the
    0.07
    emade
    0.07
     polish
    0.07
    Activations Density 0.234%

    No Known Activations