© 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. 55273
    Prev
    Next
    INDEX
    Explanations

    consecutive group

    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
    ings
    -0.10
    ÑģÑı
    -0.09
    ington
    -0.09
    ossa
    -0.09
    fred
    -0.09
    grave
    -0.09
    acos
    -0.09
    andra
    -0.09
    ache
    -0.09
    uster
    -0.09
    POSITIVE LOGITS
    roe
    0.09
    omy
    0.08
     domicile
    0.08
    ½æķ°
    0.08
    ibs
    0.08
    wald
    0.07
    /co
    0.07
    afd
    0.07
    hir
    0.07
    fdf
    0.07
    Activations Density 0.012%

    No Known Activations