© 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. 31097
    Prev
    Next
    INDEX
    Explanations

    methodology and method contexts

    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
     mend
    -0.11
    asso
    -0.11
    abay
    -0.10
    indle
    -0.10
     Cot
    -0.10
    pers
    -0.10
    out
    -0.10
    way
    -0.10
    iber
    -0.10
     Beetle
    -0.10
    POSITIVE LOGITS
    ological
    0.21
    ical
    0.19
    ologically
    0.16
    ologies
    0.14
    ically
    0.14
    ology
    0.13
    论
    0.13
    ologic
    0.12
    ologie
    0.12
    ImplOptions
    0.12
    Activations Density 0.126%

    No Known Activations