© 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. 7
    Prev
    Next
    INDEX
    Explanations

    problems/issues or characteristics

    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
     firstly
    -0.12
    ï¼Į并
    -0.11
    ô
    -0.09
     however
    -0.09
     *,
    -0.08
    ,and
    -0.08
    :↵
    -0.08
     nor
    -0.07
    ari
    -0.07
    -0.07
    POSITIVE LOGITS
     thereof
    0.19
     thereafter
    0.18
    —all
    0.17
     afterwards
    0.16
     afterward
    0.15
     therein
    0.15
     serta
    0.14
     sonst
    0.13
     sogar
    0.12
     outright
    0.12
    Activations Density 4.574%

    No Known Activations