© 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. 3777
    Prev
    Next
    INDEX
    Explanations

    self-perception, identity, expectancies, attributions

    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
     purely
    -0.11
    yat
    -0.10
    ango
    -0.09
     millions
    -0.09
     study
    -0.09
     Conc
    -0.08
     Votes
    -0.08
    enga
    -0.08
     trained
    -0.08
     human
    -0.08
    POSITIVE LOGITS
     hass
    0.09
    nov
    0.09
    emer
    0.09
     Bols
    0.08
    éri
    0.08
    outu
    0.08
    Others
    0.08
    estre
    0.08
     rehe
    0.08
     Wort
    0.08
    Activations Density 0.239%

    No Known Activations