© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56499
    Prev
    Next
    INDEX
    Explanations

    affixes for suffixes like -an, -ar, -um

    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
     Hick
    -0.09
    ital
    -0.09
     atom
    -0.08
    itin
    -0.08
    atom
    -0.08
    +(\
    -0.07
     Plum
    -0.07
    fa
    -0.07
     Iris
    -0.07
     models
    -0.07
    POSITIVE LOGITS
    ãĥ¼ãĥī
    0.10
    NDER
    0.09
    eenth
    0.09
    rale
    0.09
     chatting
    0.09
    0.09
    akov
    0.09
    argar
    0.08
    cef
    0.08
    atha
    0.08
    Activations Density 0.056%

    No Known Activations