© 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. 57990
    Prev
    Next
    INDEX
    Explanations

    comment starters

    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
     {}:
    -0.09
    ILITY
    -0.08
    #:
    -0.08
    usercontent
    -0.08
    ATUS
    -0.08
    cil
    -0.08
     gall
    -0.08
    Registrar
    -0.08
     Ross
    -0.08
    prm
    -0.08
    POSITIVE LOGITS
    rip
    0.10
    aye
    0.09
    andi
    0.09
    iram
    0.08
     subparagraph
    0.08
    ri
    0.08
     Cunningham
    0.08
     Encounter
    0.08
    erne
    0.08
    ém
    0.07
    Activations Density 0.009%

    No Known Activations