© 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. 17179
    Prev
    Next
    INDEX
    Explanations

    trend or shift

    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
     cheat
    -0.09
     obstacle
    -0.09
    uvo
    -0.09
    909
    -0.09
     untouched
    -0.09
     possession
    -0.09
     lagi
    -0.09
     devast
    -0.09
     impair
    -0.09
     unlaw
    -0.08
    POSITIVE LOGITS
     trend
    0.47
     trends
    0.45
     shift
    0.38
     Trends
    0.37
     shifts
    0.34
     Trend
    0.33
     evolution
    0.31
     trending
    0.30
     developments
    0.29
     evolving
    0.29
    Activations Density 1.301%

    No Known Activations