© 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. 133
    Prev
    Next
    INDEX
    Explanations

    accordance with

    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
    owa
    -0.10
     diss
    -0.09
    mir
    -0.09
     plag
    -0.08
    éĽĨ
    -0.08
    hetic
    -0.08
    oret
    -0.08
     Beck
    -0.08
    ÑĤÑĮ
    -0.08
    ctors
    -0.08
    POSITIVE LOGITS
    è¾ij
    0.09
    ãĤĵ
    0.09
    ukan
    0.08
    cript
    0.08
    -face
    0.08
    psilon
    0.08
    _argument
    0.08
    äºİ
    0.08
    /Framework
    0.08
    fty
    0.07
    Activations Density 0.905%

    No Known Activations