© 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. 2967
    Prev
    Next
    INDEX
    Explanations

    people's characteristics or conditions

    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
    strup
    -0.10
     Hag
    -0.08
    ins
    -0.08
    iben
    -0.08
     esac
    -0.08
    amy
    -0.08
    Ins
    -0.07
    abouts
    -0.07
    loop
    -0.07
    pter
    -0.07
    POSITIVE LOGITS
     who
    0.13
     whose
    0.11
    еÑģÑĤи
    0.11
     whom
    0.10
    whose
    0.09
    /goto
    0.09
    who
    0.09
    åĬ
    0.09
    rollo
    0.08
    erus
    0.08
    Activations Density 0.579%

    No Known Activations