© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 902
    Prev
    Next
    INDEX
    Explanations

    You can know or might

    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
     Ihnen
    -0.10
     am
    -0.09
     you
    -0.08
    was
    -0.08
     offers
    -0.08
    /n
    -0.08
    EV
    -0.08
     você
    -0.08
    offer
    -0.08
    elf
    -0.08
    POSITIVE LOGITS
     guys
    0.22
    nger
    0.20
    uu
    0.17
     yourself
    0.16
    nge
    0.16
    're
    0.16
    ’re
    0.16
    -know
    0.16
    ths
    0.15
     guessed
    0.14
    Activations Density 1.207%

    No Known Activations