© 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. 58200
    Prev
    Next
    INDEX
    Explanations

    android view methods

    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
    ing
    -0.11
    inea
    -0.10
     Tib
    -0.10
    cling
    -0.09
    azine
    -0.09
    led
    -0.09
     Dor
    -0.09
    urar
    -0.09
     Scope
    -0.09
    lage
    -0.09
    POSITIVE LOGITS
    inton
    0.09
     sop
    0.08
    isco
    0.08
    .OnClickListener
    0.08
    ilton
    0.07
    .ibm
    0.07
    rvine
    0.07
     cons
    0.07
     Cir
    0.07
     Het
    0.07
    Activations Density 0.004%

    No Known Activations