© 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. 4203
    Prev
    Next
    INDEX
    Explanations

    hit the moon

    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
     Kre
    -0.09
     circ
    -0.08
     hear
    -0.07
     Asi
    -0.07
     depos
    -0.07
    opol
    -0.07
     augmentation
    -0.06
     Flags
    -0.06
     automatic
    -0.06
    ross
    -0.06
    POSITIVE LOGITS
    -neck
    0.11
    ailer
    0.10
    peria
    0.10
    eya
    0.10
    ture
    0.10
    **/↵
    0.10
     Moder
    0.10
    isel
    0.09
     extremes
    0.09
     hay
    0.09
    Activations Density 0.220%

    No Known Activations