© 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. 1765
    Prev
    Next
    INDEX
    Explanations

    sequencing, principled, franchised, paradigm, cascading

    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
    iculty
    -0.10
     Insets
    -0.08
    enment
    -0.08
    itat
    -0.07
    illance
    -0.07
    elige
    -0.07
    ainties
    -0.07
    iates
    -0.07
    iets
    -0.07
    otle
    -0.07
    POSITIVE LOGITS
    łéĻ¤
    0.12
    (of
    0.10
    fram
    0.10
    (Of
    0.10
    ap
    0.10
    ģ
    0.10
    vig
    0.10
    -strokes
    0.10
    lect
    0.10
    gin
    0.10
    Activations Density 4.742%

    No Known Activations