© 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. 3859
    Prev
    Next
    INDEX
    Explanations

    named or called

    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
    TAIL
    -0.07
    &w
    -0.07
     Serge
    -0.07
    arez
    -0.07
    ati
    -0.07
     invisible
    -0.07
    ERA
    -0.07
    DateString
    -0.07
    TimeString
    -0.07
    Defaults
    -0.07
    POSITIVE LOGITS
     technically
    0.19
     disguised
    0.15
     rather
    0.14
     quasi
    0.14
     termed
    0.13
     instead
    0.13
     Classification
    0.13
     classified
    0.13
     Called
    0.12
     mere
    0.12
    Activations Density 0.441%

    No Known Activations