© 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. 48198
    Prev
    Next
    INDEX
    Explanations

    continuing despite failure

    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
     abrupt
    -0.10
     unexpectedly
    -0.10
     exagger
    -0.10
     circum
    -0.09
     sudden
    -0.09
     incidental
    -0.09
     coinc
    -0.09
     accurate
    -0.09
     cov
    -0.09
    ric
    -0.08
    POSITIVE LOGITS
     hoping
    0.27
     hope
    0.20
     hopes
    0.19
     hopeful
    0.18
     hoped
    0.18
     prolong
    0.16
     stubborn
    0.15
     inertia
    0.15
     Hope
    0.15
     continued
    0.15
    Activations Density 0.189%

    No Known Activations