© 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. 58041
    Prev
    Next
    INDEX
    Explanations

    A:

    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
    acman
    -0.10
     Slut
    -0.10
    chg
    -0.10
    &apos
    -0.10
    -clear
    -0.09
    ink
    -0.09
    nce
    -0.09
    arget
    -0.09
    recht
    -0.09
    uye
    -0.09
    POSITIVE LOGITS
    Loc
    0.07
     plans
    0.07
     —↵↵
    0.06
     plag
    0.06
    esen
    0.06
     ”
    0.06
     PAL
    0.06
     ALERT
    0.06
     “
    0.06
    dda
    0.06
    Activations Density 0.002%

    No Known Activations