© 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. 56721
    Prev
    Next
    INDEX
    Explanations

    Determine or Calculate

    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
    pty
    -0.09
    haus
    -0.09
    izza
    -0.08
    -ce
    -0.08
    RAIN
    -0.08
    subs
    -0.08
    mars
    -0.08
     abuses
    -0.08
     mainly
    -0.08
    POSITIVE LOGITS
    oo
    0.10
     jou
    0.08
    dar
    0.08
     syn
    0.08
    linger
    0.08
     nach
    0.08
     Wesley
    0.08
     Warren
    0.07
     associate
    0.07
    ereotype
    0.07
    Activations Density 0.008%

    No Known Activations