© 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. 113381
    Prev
    Next
    INDEX
    Explanations

    transparent window

    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
     PD
    -0.12
     Burke
    -0.10
    isons
    -0.10
    AIT
    -0.10
     Herc
    -0.10
    feas
    -0.10
     enhancement
    -0.10
     Enhancement
    -0.09
    rote
    -0.09
    quo
    -0.09
    POSITIVE LOGITS
     fluct
    0.10
     models
    0.10
     thousand
    0.09
    sterdam
    0.09
     traff
    0.08
     aber
    0.08
    âĢ¦it
    0.08
     Models
    0.08
     turnover
    0.08
     populous
    0.08
    Activations Density 0.001%

    No Known Activations