© 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. 8300
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
    ipa
    -0.09
     Kemp
    -0.09
    trl
    -0.09
    -Methods
    -0.08
     Herz
    -0.08
    uber
    -0.08
    coop
    -0.08
    anel
    -0.08
    psilon
    -0.08
    ooled
    -0.08
    POSITIVE LOGITS
     HOWEVER
    0.10
    åķĨ
    0.09
    af
    0.09
    lee
    0.08
    å®ĭ
    0.08
    ìĭ
    0.08
     Seriously
    0.08
     ranger
    0.08
    town
    0.08
     Ranger
    0.08
    Activations Density 0.442%

    No Known Activations