© 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. 1918
    Prev
    Next
    INDEX
    Explanations

    use of

    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
     useful
    -0.12
     usable
    -0.10
    acro
    -0.10
     useless
    -0.10
    UserProfile
    -0.10
    _using
    -0.10
     usefulness
    -0.09
    User
    -0.09
     using
    -0.09
     Useful
    -0.09
    POSITIVE LOGITS
    fully
    0.26
    ful
    0.17
    fulness
    0.17
    lessly
    0.16
    cols
    0.16
    age
    0.15
    FUL
    0.15
    full
    0.14
     sparing
    0.13
    lessness
    0.12
    Activations Density 0.851%

    No Known Activations