© 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. 4706
    Prev
    Next
    INDEX
    Explanations

    reviews and information

    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
    ÑģÑĤв
    -0.08
    ÛĮÙĨ
    -0.08
    ento
    -0.08
    igne
    -0.07
    odate
    -0.07
    ots
    -0.07
     pes
    -0.07
    van
    -0.07
    Ī
    -0.07
     resent
    -0.07
    POSITIVE LOGITS
    aiser
    0.11
    orial
    0.10
    ee
    0.10
    able
    0.09
    oria
    0.09
    ued
    0.09
    theless
    0.09
    ody
    0.09
    ies
    0.09
    adium
    0.09
    Activations Density 0.054%

    No Known Activations