© 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. 61559
    Prev
    Next
    INDEX
    Explanations

    make results manageable or safe

    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
    ÑģÑĤÑĮ
    -0.12
    VAS
    -0.09
     replacements
    -0.09
     ward
    -0.09
     eviction
    -0.09
    ihilation
    -0.09
     shorthand
    -0.09
     autof
    -0.09
     NONINFRINGEMENT
    -0.08
    ÑģÑĭ
    -0.08
    POSITIVE LOGITS
     sanity
    0.09
     uncont
    0.09
     preserve
    0.09
     manageable
    0.09
     conserv
    0.09
     preserved
    0.09
     conserve
    0.08
     safety
    0.08
     preserves
    0.08
    ahr
    0.08
    Activations Density 0.091%

    No Known Activations