© 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. 114070
    Prev
    Next
    INDEX
    Explanations

    abandoned, decay, ruins

    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
     zo
    -0.09
     bliss
    -0.09
     busy
    -0.09
     Tray
    -0.09
     waking
    -0.09
     refresh
    -0.09
    Infinity
    -0.09
     tray
    -0.09
     mates
    -0.09
     Accred
    -0.08
    POSITIVE LOGITS
     abandoned
    0.30
     decay
    0.29
     abandonment
    0.25
     Decay
    0.25
     rust
    0.25
     rusty
    0.24
     rubble
    0.22
    decay
    0.22
     crumbling
    0.22
     abandon
    0.22
    Activations Density 0.428%

    No Known Activations