© 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. 32762
    Prev
    Next
    INDEX
    Explanations

    runaway or Runner

    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
     miser
    -0.10
    isp
    -0.08
     nep
    -0.08
     plaza
    -0.08
     chron
    -0.08
     muster
    -0.08
     walkthrough
    -0.08
    vsp
    -0.08
     rainy
    -0.07
     unrecognized
    -0.07
    POSITIVE LOGITS
    ibi
    0.12
    VERY
    0.11
    nos
    0.11
    enses
    0.11
    psc
    0.10
    /OR
    0.10
     cuff
    0.10
     Berger
    0.10
    oram
    0.10
    .RunWith
    0.09
    Activations Density 0.048%

    No Known Activations