© 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. 3415
    Prev
    Next
    INDEX
    Explanations

    suited for suitability

    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
     access
    -0.08
     Tel
    -0.08
    Con
    -0.08
     pedest
    -0.08
     decl
    -0.08
     Klein
    -0.08
     legitim
    -0.08
     tim
    -0.08
    uman
    -0.08
     Con
    -0.08
    POSITIVE LOGITS
     suitability
    0.10
     suited
    0.10
     matched
    0.09
     appeal
    0.09
     excel
    0.09
    Ñĥж
    0.09
    lik
    0.09
    aga
    0.09
     Appeal
    0.09
     disproportionate
    0.08
    Activations Density 0.322%

    No Known Activations