© 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. 292
    Prev
    Next
    INDEX
    Explanations

    be a, c, j, w, (, -, g, s, l

    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
    ¸
    -0.08
     accounted
    -0.07
    els
    -0.07
    Ros
    -0.07
    ·
    -0.07
    163
    -0.07
     tud
    -0.07
    iding
    -0.07
    æľ¬
    -0.07
     hitters
    -0.07
    POSITIVE LOGITS
    inka
    0.10
    zimmer
    0.10
    quiv
    0.10
     asm
    0.10
    _SUPPLY
    0.10
    aura
    0.10
    aire
    0.10
    vor
    0.09
    mins
    0.09
    bote
    0.09
    Activations Density 0.184%

    No Known Activations