© 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. 5759
    Prev
    Next
    INDEX
    Explanations

    building up gradually

    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
     nostalg
    -0.10
     ðŁĴ
    -0.08
     Jah
    -0.08
     Hod
    -0.08
     Aging
    -0.08
     spl
    -0.08
     Analyzer
    -0.08
    Spl
    -0.08
     shutter
    -0.08
     splash
    -0.08
    POSITIVE LOGITS
     gradually
    0.33
     escalation
    0.33
     escalating
    0.33
     gradual
    0.33
     cresc
    0.32
     progressively
    0.30
     escalate
    0.29
     buildup
    0.29
     slowly
    0.28
     increasing
    0.27
    Activations Density 0.107%

    No Known Activations