© 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. 31712
    Prev
    Next
    INDEX
    Explanations

    cracks and fractures

    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
     mang
    -0.11
     LOCK
    -0.11
     keyed
    -0.11
     crow
    -0.11
    acid
    -0.11
    ikit
    -0.11
     ench
    -0.11
     tit
    -0.11
     flavor
    -0.10
     Nie
    -0.10
    POSITIVE LOGITS
     cracks
    0.28
     crack
    0.25
     cracking
    0.25
     cracked
    0.24
     fiss
    0.23
     Crack
    0.21
     splits
    0.18
     splitting
    0.17
     fractures
    0.17
     fracture
    0.16
    Activations Density 0.145%

    No Known Activations