© 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. 53793
    Prev
    Next
    INDEX
    Explanations

    statement of need or possession

    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
     Sr
    -0.10
    ics
    -0.10
     suppression
    -0.10
     threat
    -0.10
     "["
    -0.10
    anj
    -0.09
    ids
    -0.09
    jar
    -0.09
     sender
    -0.09
     falta
    -0.09
    POSITIVE LOGITS
    unde
    0.08
     shortly
    0.07
    erb
    0.07
     late
    0.07
    onest
    0.07
    andalone
    0.06
     breeze
    0.06
    birthdate
    0.06
     oci
    0.06
    /render
    0.06
    Activations Density 0.018%

    No Known Activations