© 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. 2909
    Prev
    Next
    INDEX
    Explanations

    initialisms followed by letters

    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
    adan
    -0.08
     pretend
    -0.08
     thro
    -0.07
     Kov
    -0.07
     frm
    -0.07
     frankly
    -0.07
    ambre
    -0.07
    ve
    -0.07
     sqr
    -0.07
    archical
    -0.07
    POSITIVE LOGITS
     Valk
    0.10
    quine
    0.09
    mile
    0.09
     volta
    0.09
    inis
    0.09
    Äĩi
    0.09
    agers
    0.09
    <!--<
    0.09
    aub
    0.09
    (es
    0.09
    Activations Density 0.389%

    No Known Activations