© 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. 3320
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by text

    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
    amon
    -0.08
    uber
    -0.07
    than
    -0.07
     espec
    -0.07
     cart
    -0.07
    ienes
    -0.07
     Romans
    -0.07
     offic
    -0.07
     Haupt
    -0.07
    uste
    -0.07
    POSITIVE LOGITS
    bang
    0.11
     Exceptions
    0.10
     unlike
    0.10
    ora
    0.10
     Hodg
    0.09
     Contrast
    0.09
    gard
    0.09
    rez
    0.09
    kan
    0.09
     inters
    0.09
    Activations Density 0.579%

    No Known Activations