© 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. 2703
    Prev
    Next
    INDEX
    Explanations

    which is the

    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
    ngo
    -0.08
     subtly
    -0.08
    Screen
    -0.08
     Anything
    -0.08
     basically
    -0.07
    ewater
    -0.07
    raison
    -0.07
    lights
    -0.07
     screen
    -0.07
    yd
    -0.07
    POSITIVE LOGITS
    (s
    0.11
    Rib
    0.09
    enas
    0.09
    ombat
    0.08
     chose
    0.08
    onz
    0.08
    ossier
    0.08
    ann
    0.08
     ins
    0.08
     Sea
    0.08
    Activations Density 0.018%

    No Known Activations