© 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. 61231
    Prev
    Next
    INDEX
    Explanations

    same problem encountered

    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
     concealed
    -0.08
     Casey
    -0.08
    /session
    -0.08
    ि
    -0.07
    iez
    -0.07
    tz
    -0.07
    ROC
    -0.07
     Robin
    -0.07
     authorized
    -0.07
     Avalanche
    -0.07
    POSITIVE LOGITS
     coincide
    0.11
     exact
    0.11
    exact
    0.10
    oll
    0.10
     Inputs
    0.10
    pose
    0.09
    orest
    0.09
     Exact
    0.09
     cog
    0.09
    inka
    0.09
    Activations Density 0.054%

    No Known Activations