© 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. 48112
    Prev
    Next
    INDEX
    Explanations

    finding a solution

    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
     spoil
    -0.11
     enrich
    -0.10
     Enjoy
    -0.09
     Cot
    -0.09
     someday
    -0.08
     enjoying
    -0.08
     truthful
    -0.08
     Trident
    -0.08
     thrill
    -0.08
     predicting
    -0.08
    POSITIVE LOGITS
     solution
    0.22
     desperation
    0.22
     Solution
    0.21
     resort
    0.21
     desperate
    0.20
    solution
    0.20
    Solution
    0.19
     SOLUTION
    0.19
     solutions
    0.19
     Solutions
    0.19
    Activations Density 0.183%

    No Known Activations