© 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. 61586
    Prev
    Next
    INDEX
    Explanations

    not followed by definition

    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
    exact
    -0.09
     exact
    -0.09
    inda
    -0.09
    Exact
    -0.09
    enga
    -0.09
     Oliver
    -0.09
     distra
    -0.09
     sophistic
    -0.08
     indeed
    -0.08
     pies
    -0.08
    POSITIVE LOGITS
    hq
    0.09
    bart
    0.08
     galer
    0.08
     jun
    0.08
    ift
    0.08
     derp
    0.08
    ÑĢ
    0.08
     ACTIVE
    0.08
     tempfile
    0.08
     Onion
    0.08
    Activations Density 0.055%

    No Known Activations