© 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. 33823
    Prev
    Next
    INDEX
    Explanations

    as in, like, meaning

    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
    indo
    -0.09
    elman
    -0.09
     indirect
    -0.08
     DISCLAIMER
    -0.08
     Dort
    -0.08
     cach
    -0.08
     Stones
    -0.08
    esson
    -0.08
     kaum
    -0.08
    uv
    -0.08
    POSITIVE LOGITS
     as
    0.25
     like
    0.22
     meaning
    0.19
     Like
    0.17
    -as
    0.16
    Like
    0.16
    like
    0.16
     Meaning
    0.15
    (as
    0.15
    meaning
    0.15
    Activations Density 0.145%

    No Known Activations