© 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. 58042
    Prev
    Next
    INDEX
    Explanations

    coding visual layout

    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
     Commentary
    -0.08
     Morton
    -0.08
    utta
    -0.07
    /~
    -0.07
    quila
    -0.07
    sie
    -0.07
    KI
    -0.07
     ns
    -0.07
     Psr
    -0.07
    toi
    -0.06
    POSITIVE LOGITS
    vé
    0.11
    .launch
    0.10
    omon
    0.10
    象
    0.10
     constituent
    0.09
     cue
    0.09
     Kor
    0.09
    ick
    0.09
    onas
    0.09
     cues
    0.09
    Activations Density 0.011%

    No Known Activations