© 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. 89679
    Prev
    Next
    INDEX
    Explanations

    cyclical or cyclic concepts

    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
    esper
    -0.09
    REA
    -0.09
    quir
    -0.08
     scattered
    -0.08
    inch
    -0.08
     guild
    -0.08
    _CN
    -0.08
     trembling
    -0.07
     spreading
    -0.07
     Hearts
    -0.07
    POSITIVE LOGITS
     cycle
    0.34
     cycles
    0.33
     Cycle
    0.31
    cycle
    0.29
    Cycle
    0.28
     loop
    0.27
     cycling
    0.27
    -cycle
    0.27
     cyc
    0.27
     loops
    0.26
    Activations Density 0.496%

    No Known Activations