© 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. 33030
    Prev
    Next
    INDEX
    Explanations

    of a/an/the/what

    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
    nst
    -0.10
    FX
    -0.09
     Loose
    -0.09
    VN
    -0.09
     territory
    -0.09
    omba
    -0.09
    .Safe
    -0.09
    nat
    -0.09
    稿
    -0.09
    fulness
    -0.08
    POSITIVE LOGITS
     ticking
    0.10
     an
    0.10
     a
    0.09
     mess
    0.09
     Blazers
    0.08
     Grass
    0.08
    aload
    0.08
    091
    0.08
    akis
    0.08
     Hess
    0.07
    Activations Density 0.016%

    No Known Activations