© 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. 3958
    Prev
    Next
    INDEX
    Explanations

    blue and common phrases

    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
    undi
    -0.10
     Tribune
    -0.10
    osate
    -0.10
    omaly
    -0.09
    /text
    -0.09
    erk
    -0.09
    illian
    -0.09
    upt
    -0.08
    unda
    -0.08
    IMER
    -0.08
    POSITIVE LOGITS
    prints
    0.13
    berries
    0.13
    berry
    0.10
    -collar
    0.10
    zy
    0.09
    hof
    0.09
    plays
    0.09
    printing
    0.08
    arga
    0.08
    �t
    0.08
    Activations Density 0.122%

    No Known Activations