© 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. 54787
    Prev
    Next
    INDEX
    Explanations

    *in vitro* or *in vivo*

    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
     duty
    -0.09
    à¸ĵ
    -0.08
     Duty
    -0.08
     Written
    -0.07
    opes
    -0.07
    asca
    -0.07
     Sense
    -0.07
     tower
    -0.07
    ade
    -0.07
    èģĶ
    -0.07
    POSITIVE LOGITS
    .vo
    0.10
    neh
    0.10
    ks
    0.10
    /out
    0.10
     Nich
    0.09
    ssc
    0.09
    ced
    0.09
    itas
    0.09
    .ud
    0.09
    aul
    0.09
    Activations Density 0.007%

    No Known Activations