© 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. 57890
    Prev
    Next
    INDEX
    Explanations

    numbers of letters

    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
    onne
    -0.08
    intro
    -0.07
     ar
    -0.07
     pigeon
    -0.07
     Alf
    -0.07
    summ
    -0.07
     fuller
    -0.07
    rc
    -0.07
    si
    -0.07
    	Copyright
    -0.07
    POSITIVE LOGITS
     stitches
    0.09
    apeut
    0.09
    Fr
    0.08
    Advertisement
    0.08
    ãĥĪ
    0.08
    bra
    0.08
     dear
    0.08
     chaud
    0.08
    _BT
    0.08
    Son
    0.08
    Activations Density 0.001%

    No Known Activations