© 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. 48527
    Prev
    Next
    INDEX
    Explanations

    negations or auxiliary verbs following pronouns

    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
    issen
    -0.12
     obliv
    -0.10
     Unknown
    -0.10
     Forgotten
    -0.10
    Inactive
    -0.09
     forgotten
    -0.09
     Neg
    -0.09
    nil
    -0.09
    为空
    -0.09
     unread
    -0.09
    POSITIVE LOGITS
     doesn
    0.38
     isn
    0.37
    ä¸į
    0.36
     nicht
    0.36
     aren
    0.35
     neither
    0.33
     don
    0.33
     âīł
    0.32
     wasn
    0.32
     not
    0.32
    Activations Density 0.856%

    No Known Activations