© 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. 4102
    Prev
    Next
    INDEX
    Explanations

    dispose, dispositions, 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
    olor
    -0.09
     Spot
    -0.09
    ÑĢав
    -0.08
    ance
    -0.08
    woman
    -0.08
    lag
    -0.08
    (es
    -0.07
    antes
    -0.07
     jer
    -0.07
    lights
    -0.07
    POSITIVE LOGITS
    itional
    0.12
    äºİ
    0.12
    eree
    0.10
    INCT
    0.10
    ymous
    0.10
    .fm
    0.10
    fully
    0.10
    ties
    0.09
    tty
    0.09
    .activate
    0.09
    Activations Density 0.032%

    No Known Activations