© 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. 5360
    Prev
    Next
    INDEX
    Explanations

    achieved something

    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
     unnecessarily
    -0.13
     purposely
    -0.13
     deliberately
    -0.13
     necessarily
    -0.13
     willingly
    -0.12
     gladly
    -0.12
     knowingly
    -0.11
     preferably
    -0.11
     intentionally
    -0.11
     gerne
    -0.11
    POSITIVE LOGITS
     successfully
    0.26
     Successfully
    0.19
     despite
    0.19
     enough
    0.17
     somehow
    0.17
     succesfully
    0.17
     sufficiently
    0.16
     thanks
    0.15
     sucess
    0.14
    successfully
    0.14
    Activations Density 0.261%

    No Known Activations