© 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. 57238
    Prev
    Next
    INDEX
    Explanations

    _label, _desc, title, _text

    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
    drs
    -0.09
    gars
    -0.09
    Infos
    -0.09
    efs
    -0.09
    kop
    -0.09
     COLL
    -0.09
    abl
    -0.08
    ]){
    -0.08
    byss
    -0.08
     Prim
    -0.08
    POSITIVE LOGITS
     chopping
    0.09
     Duch
    0.08
     hap
    0.08
     ground
    0.08
    cel
    0.08
     Everybody
    0.08
     Neal
    0.08
     Thumb
    0.07
    heim
    0.07
     IN
    0.07
    Activations Density 0.002%

    No Known Activations