© 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. 3160
    Prev
    Next
    INDEX
    Explanations

    formed with recess

    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
    lick
    -0.09
    vido
    -0.08
     favor
    -0.08
    ORA
    -0.08
    Pocket
    -0.08
     properly
    -0.08
    ippo
    -0.08
     (){
    -0.08
     Crist
    -0.08
     complimentary
    -0.08
    POSITIVE LOGITS
     unnecessarily
    0.10
     Must
    0.10
     MUST
    0.09
     inconsist
    0.09
     must
    0.09
    Must
    0.09
     leaked
    0.09
    eka
    0.09
    aring
    0.08
     unrestricted
    0.08
    Activations Density 0.204%

    No Known Activations