© 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. 58201
    Prev
    Next
    INDEX
    Explanations

    touchdowns, °C, ,

    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
    isse
    -0.08
     admitted
    -0.08
     admissions
    -0.07
    ismatic
    -0.07
     daily
    -0.07
     admission
    -0.07
    hy
    -0.07
    rement
    -0.07
     Savage
    -0.07
    ador
    -0.07
    POSITIVE LOGITS
    zon
    0.11
    otate
    0.09
     crow
    0.09
     Norm
    0.09
     norm
    0.09
    onte
    0.09
     centrif
    0.09
    awy
    0.09
     grief
    0.09
     NotImplemented
    0.08
    Activations Density 0.020%

    No Known Activations