© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 54350
    Prev
    Next
    INDEX
    Explanations

    -fPIC or -fPIC=1

    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
    guided
    -0.08
     punches
    -0.07
    Summary
    -0.07
     keyof
    -0.07
     punch
    -0.07
    aqu
    -0.06
     Ultimate
    -0.06
     Bowen
    -0.06
     summary
    -0.06
     mass
    -0.06
    POSITIVE LOGITS
    ndl
    0.10
     bil
    0.10
     Seiten
    0.10
    -begin
    0.09
    234
    0.09
    stead
    0.09
    /=
    0.09
     confl
    0.09
    reno
    0.09
    lane
    0.09
    Activations Density 0.002%

    No Known Activations