© 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. 112134
    Prev
    Next
    INDEX
    Explanations

    continuing where left off

    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
     downgrade
    -0.09
     hol
    -0.09
    chg
    -0.08
    892
    -0.08
     sober
    -0.08
     nominate
    -0.08
    asan
    -0.08
     Nash
    -0.08
    aise
    -0.08
    ysz
    -0.08
    POSITIVE LOGITS
     resumed
    0.49
     resume
    0.46
     continuation
    0.44
     unfinished
    0.43
     resumes
    0.42
     Resume
    0.38
    resume
    0.37
    unfinished
    0.32
     continu
    0.32
     continuing
    0.32
    Activations Density 0.369%

    No Known Activations