© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 116084
    Prev
    Next
    INDEX
    Explanations

    languages and translations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bans
    -0.11
     Kum
    -0.10
     unlink
    -0.10
     THROW
    -0.09
    quat
    -0.09
     wore
    -0.09
    syscall
    -0.09
     taped
    -0.08
     Triple
    -0.08
     Darling
    -0.08
    POSITIVE LOGITS
     English
    0.17
     translations
    0.16
     translation
    0.15
     transl
    0.15
     Españ
    0.15
     Deutsch
    0.14
     localization
    0.14
     UTF
    0.14
     locale
    0.14
     localized
    0.14
    Activations Density 0.415%

    No Known Activations