© 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. 57526
    Prev
    Next
    INDEX
    Explanations

    construction of such existence

    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
     props
    -0.11
     prop
    -0.10
     arsen
    -0.10
     graduated
    -0.10
     Samurai
    -0.09
     Props
    -0.09
     Tar
    -0.09
     flu
    -0.09
     Cant
    -0.09
    alin
    -0.09
    POSITIVE LOGITS
     fry
    0.08
     Corrections
    0.08
     Kul
    0.08
     ÑĩеÑĢ
    0.07
    å¾ħ
    0.07
    Pink
    0.07
     pall
    0.07
    RIEND
    0.07
    °
    0.07
    mans
    0.07
    Activations Density 0.018%

    No Known Activations