© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 91916
    Prev
    Next
    INDEX
    Explanations

    questions and possessives

    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
     arbitrary
    -0.10
     surely
    -0.10
     Arbitrary
    -0.10
     everywhere
    -0.09
     certainly
    -0.09
    ↵     ↵
    -0.09
    wer
    -0.08
     apparently
    -0.08
    abra
    -0.08
    Apparently
    -0.08
    POSITIVE LOGITS
     yourself
    0.20
     yourselves
    0.19
     your
    0.17
    your
    0.16
    ?</
    0.16
    /or
    0.15
     _____
    0.15
    (s
    0.15
     ваÑĪ
    0.15
     MOST
    0.15
    Activations Density 0.172%

    No Known Activations