© 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. 54414
    Prev
    Next
    INDEX
    Explanations

    post count

    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
    adox
    -0.09
    omy
    -0.09
    dit
    -0.09
    jem
    -0.09
    ura
    -0.09
    agra
    -0.08
    unu
    -0.08
    [url
    -0.08
     Wend
    -0.08
    Votes
    -0.08
    POSITIVE LOGITS
    aket
    0.10
    avi
    0.10
    onta
    0.09
    lements
    0.09
     sew
    0.08
     prime
    0.08
     capped
    0.08
     }č↵č↵č↵č↵
    0.08
    vol
    0.08
    placing
    0.08
    Activations Density 0.001%

    No Known Activations