© 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. 27447
    Prev
    Next
    INDEX
    Explanations

    imagined scenarios

    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
    oire
    -0.10
    oze
    -0.09
     understandably
    -0.09
     recht
    -0.09
     occasional
    -0.09
     WTF
    -0.08
     hardly
    -0.08
     fetish
    -0.08
     promptly
    -0.08
    IDA
    -0.08
    POSITIVE LOGITS
     hypothetical
    0.25
     hypoth
    0.19
     someday
    0.19
     imagined
    0.16
     imaginary
    0.14
     would
    0.14
     Would
    0.13
    Would
    0.13
    would
    0.13
     similarly
    0.12
    Activations Density 0.038%

    No Known Activations