© 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. 2024
    Prev
    Next
    INDEX
    Explanations

    considering alternatives or options

    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
     gloss
    -0.09
     reordered
    -0.09
    aura
    -0.08
     foreground
    -0.08
    andr
    -0.08
    -comments
    -0.08
     associated
    -0.08
     оÑģ
    -0.08
     governing
    -0.08
    @Api
    -0.08
    POSITIVE LOGITS
     alternatives
    0.27
     alternative
    0.27
     resort
    0.24
     instead
    0.22
     alternatively
    0.22
     Alternative
    0.21
     recourse
    0.20
    Alternative
    0.19
     Instead
    0.19
     alternate
    0.18
    Activations Density 3.129%

    No Known Activations