© 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. 960
    Prev
    Next
    INDEX
    Explanations

    return to or back from

    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
    ador
    -0.11
    lik
    -0.10
    -thumb
    -0.10
    yb
    -0.10
    _deinit
    -0.10
    uren
    -0.10
    esser
    -0.10
    mux
    -0.10
    vos
    -0.09
    otor
    -0.09
    POSITIVE LOGITS
    /re
    0.15
    /rec
    0.12
     whence
    0.10
    (return
    0.10
    /reset
    0.09
     lost
    0.09
     home
    0.09
    /rest
    0.08
    (Return
    0.08
     lại
    0.08
    Activations Density 0.960%

    No Known Activations