© 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. 785
    Prev
    Next
    INDEX
    Explanations

    match_parent / fill_parent

    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
     misd
    -0.10
    atre
    -0.09
    {return
    -0.09
    oes
    -0.08
     fucking
    -0.08
    oe
    -0.08
     '&'
    -0.08
     ...\
    -0.08
     hare
    -0.08
    TOCOL
    -0.08
    POSITIVE LOGITS
    üz
    0.08
    rien
    0.08
    /calendar
    0.08
    VIN
    0.08
     Duis
    0.08
     ="";↵
    0.08
    :";č↵
    0.07
     innings
    0.07
     *);↵↵
    0.07
     teng
    0.07
    Activations Density 3.096%

    No Known Activations