© 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. 57241
    Prev
    Next
    INDEX
    Explanations

    directory paths

    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
    LLL
    -0.08
    illy
    -0.08
    ½Ķ
    -0.08
    ɵ
    -0.07
     Roads
    -0.07
     horizontally
    -0.07
    ized
    -0.07
     aud
    -0.07
    esi
    -0.07
    atr
    -0.07
    POSITIVE LOGITS
    VIP
    0.10
    aper
    0.09
    undle
    0.09
     Alive
    0.09
    uxtap
    0.09
    AFX
    0.09
    HQ
    0.09
    hq
    0.09
    alive
    0.09
    apers
    0.08
    Activations Density 0.065%

    No Known Activations