© 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. 3366
    Prev
    Next
    INDEX
    Explanations

    whatever / whoever / compensation

    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
     nir
    -0.10
    adir
    -0.10
    almost
    -0.09
     briefly
    -0.09
    corr
    -0.09
     Relay
    -0.09
     prank
    -0.09
     Butt
    -0.09
    ÙĬر
    -0.09
    resse
    -0.09
    POSITIVE LOGITS
     whatever
    0.10
    zy
    0.09
     whoever
    0.08
    ocode
    0.08
    isel
    0.08
    292
    0.08
     Fork
    0.08
     compensation
    0.08
     separately
    0.07
     inherent
    0.07
    Activations Density 0.183%

    No Known Activations