© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115410
    Prev
    Next
    INDEX
    Explanations

    dining, eating, playing, studying, taught

    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
     afin
    -0.10
    eness
    -0.10
     Ost
    -0.10
     equivalents
    -0.10
    annel
    -0.09
    129
    -0.09
    ELS
    -0.09
    CTS
    -0.09
    TC
    -0.09
    rias
    -0.09
    POSITIVE LOGITS
     elsewhere
    0.18
     abroad
    0.18
     alongside
    0.17
     aboard
    0.13
     beside
    0.13
     outdoors
    0.13
     here
    0.12
    /work
    0.12
     chez
    0.12
     indoors
    0.12
    Activations Density 0.351%

    No Known Activations