© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8394
    Prev
    Next
    INDEX
    Explanations

    ultrasonography

    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
    iske
    -0.08
     lim
    -0.08
    ação
    -0.08
    aksi
    -0.08
    (pos
    -0.08
    iot
    -0.08
     Sentence
    -0.08
    GRAM
    -0.07
    екÑĤ
    -0.07
     prec
    -0.07
    POSITIVE LOGITS
     waves
    0.12
    adar
    0.10
     wave
    0.10
     Waves
    0.10
     sporting
    0.09
     effect
    0.09
     cuffs
    0.09
     Dop
    0.09
     practitioner
    0.09
     clipboard
    0.09
    Activations Density 0.141%

    No Known Activations