© 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. 116957
    Prev
    Next
    INDEX
    Explanations

    punctuation and case variants of contains

    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
    clin
    -0.11
    Declare
    -0.10
    Notifications
    -0.10
     chiff
    -0.10
    gis
    -0.10
    afa
    -0.10
    ooth
    -0.10
    gress
    -0.10
     darn
    -0.10
    tel
    -0.10
    POSITIVE LOGITS
     contains
    0.13
     contain
    0.12
     Contains
    0.12
     contained
    0.11
    contains
    0.10
    Contains
    0.10
    !:
    0.09
    :
    0.09
    !--
    0.09
     mature
    0.09
    Activations Density 0.019%

    No Known Activations