© 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. 16712
    Prev
    Next
    INDEX
    Explanations

    fainting or collapse

    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
     itch
    -0.11
     reluct
    -0.10
     shredd
    -0.10
     unsett
    -0.09
     Repair
    -0.09
     shred
    -0.09
     indiscrim
    -0.09
     grinder
    -0.09
     pest
    -0.08
     divorce
    -0.08
    POSITIVE LOGITS
     faint
    0.27
     dizzy
    0.24
     stead
    0.21
     collapse
    0.20
     collapsing
    0.19
     stability
    0.19
     weakness
    0.18
     collapses
    0.18
     collapsed
    0.18
     stabil
    0.18
    Activations Density 0.149%

    No Known Activations