© 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. 49114
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
     pers
    -0.09
    asse
    -0.08
     Bale
    -0.07
     remar
    -0.07
     Match
    -0.07
    èIJ
    -0.07
    orte
    -0.07
    alse
    -0.07
    resource
    -0.07
    ault
    -0.07
    POSITIVE LOGITS
    ATES
    0.11
    iors
    0.10
    âĢij
    0.10
     вÑĭп
    0.10
    ék
    0.10
    LOC
    0.10
    _flutter
    0.10
     polishing
    0.10
     Salv
    0.10
    æĿŁ
    0.10
    Activations Density 0.001%

    No Known Activations