© 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. 116847
    Prev
    Next
    INDEX
    Explanations

    but ultimately interrupted

    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
     initially
    -0.10
     unprotected
    -0.09
    .edu
    -0.08
    SE
    -0.08
     retal
    -0.08
    ikh
    -0.08
     tried
    -0.08
     Pants
    -0.08
     Trying
    -0.08
     Sears
    -0.08
    POSITIVE LOGITS
     suddenly
    0.20
     ultimately
    0.20
     abruptly
    0.18
     Ultimately
    0.17
     prevented
    0.16
     abrupt
    0.16
     thwart
    0.16
     sudden
    0.16
     chick
    0.15
     preventing
    0.14
    Activations Density 0.131%

    No Known Activations