© 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. 58690
    Prev
    Next
    INDEX
    Explanations

    showing specific achievements

    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
     veterans
    -0.10
    iku
    -0.10
     vac
    -0.10
    osite
    -0.10
     toned
    -0.09
     jog
    -0.09
    olvable
    -0.09
    INE
    -0.09
    alc
    -0.09
    hints
    -0.09
    POSITIVE LOGITS
     elsewhere
    0.09
     abroad
    0.09
    lijah
    0.08
     Caj
    0.07
    обÑĢаÐ
    0.07
    /plugin
    0.07
     Spin
    0.07
    ajan
    0.07
     ensl
    0.07
    ongan
    0.07
    Activations Density 0.116%

    No Known Activations