© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 61700
    Prev
    Next
    INDEX
    Explanations

    code keywords: break, return

    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
     nurs
    -0.07
     dying
    -0.07
     equivalent
    -0.06
     dy
    -0.06
    aps
    -0.06
     fy
    -0.06
    ark
    -0.06
    886
    -0.06
     Sanctuary
    -0.06
    Ħ
    -0.06
    POSITIVE LOGITS
    (using
    0.11
    oji
    0.11
    piler
    0.10
    kre
    0.10
     valign
    0.10
    å§
    0.10
    clist
    0.10
    _ok
    0.10
     savedInstanceState
    0.10
    .springboot
    0.10
    Activations Density 0.008%

    No Known Activations