© 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. 1455
    Prev
    Next
    INDEX
    Explanations

    c followed by assignment or function call

    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
    olumn
    -0.11
    ache
    -0.10
    chn
    -0.09
    CP
    -0.09
    ryptography
    -0.08
    ounty
    -0.08
    CHAT
    -0.08
    cxx
    -0.08
    CCI
    -0.08
    chat
    -0.08
    POSITIVE LOGITS
    apult
    0.10
    -cut
    0.10
    enance
    0.10
    ifornia
    0.09
    liness
    0.09
    ertino
    0.09
    mere
    0.09
    plx
    0.09
    shaft
    0.09
    tte
    0.09
    Activations Density 4.502%

    No Known Activations