© 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. 55004
    Prev
    Next
    INDEX
    Explanations

    so much / so few

    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
     enough
    -0.12
     Enough
    -0.11
    led
    -0.09
     Strand
    -0.09
     seedu
    -0.09
    orse
    -0.09
     Sé
    -0.09
    è¶
    -0.09
    ake
    -0.09
     clearer
    -0.08
    POSITIVE LOGITS
    cai
    0.10
    plode
    0.10
    onia
    0.09
    /if
    0.09
    elas
    0.09
    kaar
    0.09
    anh
    0.08
     Dien
    0.08
    xes
    0.08
    ARRIER
    0.08
    Activations Density 0.017%

    No Known Activations