© 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. 4254
    Prev
    Next
    INDEX
    Explanations

    cannot be done

    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
    aight
    -0.11
    étique
    -0.10
    (indent
    -0.10
    iles
    -0.09
    ringe
    -0.09
     estr
    -0.09
    ores
    -0.09
     Forgotten
    -0.09
    ndx
    -0.09
     missed
    -0.09
    POSITIVE LOGITS
     imposs
    0.22
     impossible
    0.20
     Impossible
    0.18
     realistically
    0.18
     inherently
    0.17
     cannot
    0.15
    cannot
    0.14
     unavoid
    0.14
     unavoidable
    0.13
    Impossible
    0.13
    Activations Density 0.416%

    No Known Activations