© 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. 480
    Prev
    Next
    INDEX
    Explanations

    each other

    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
    �t
    -0.21
    ;t
    -0.12
    &apos
    -0.11
    ?t
    -0.11
    ÃŃt
    -0.11
    icator
    -0.10
    `t
    -0.10
    ’T
    -0.09
    ´t
    -0.09
    Breadcrumb
    -0.08
    POSITIVE LOGITS
    arde
    0.19
    keletal
    0.18
    brane
    0.18
    nown
    0.17
    erable
    0.15
    lyph
    0.15
    SSION
    0.14
    udence
    0.14
    RODUCTION
    0.14
    rious
    0.14
    Activations Density 0.122%

    No Known Activations