© 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. 8312
    Prev
    Next
    INDEX
    Explanations

    problems and solutions

    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
    Negative Logits
     tipped
    -0.10
     complained
    -0.08
    obb
    -0.08
    arse
    -0.08
    emb
    -0.08
     Cru
    -0.08
    tas
    -0.08
     nostalg
    -0.08
    riba
    -0.08
     Vig
    -0.08
    POSITIVE LOGITS
     reduction
    0.14
     prevention
    0.14
     relief
    0.13
     elimination
    0.13
     erad
    0.13
     allev
    0.13
     Prevention
    0.12
     mitigation
    0.12
     Reduction
    0.12
     removal
    0.12
    Activations Density 0.551%

    No Known Activations