© 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. 47840
    Prev
    Next
    INDEX
    Explanations

    implicit, hidden meaning, underlying

    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
     confusion
    -0.12
     bewild
    -0.10
     confusing
    -0.10
     confuse
    -0.10
    athi
    -0.09
     Cot
    -0.09
     confused
    -0.09
     fluid
    -0.09
    agas
    -0.09
     [#
    -0.08
    POSITIVE LOGITS
     implicit
    0.38
     implied
    0.37
     Implicit
    0.31
     implicitly
    0.29
    implicit
    0.29
    Implicit
    0.27
     unst
    0.27
     implication
    0.25
     tac
    0.25
     underlying
    0.23
    Activations Density 0.106%

    No Known Activations