© 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. 113361
    Prev
    Next
    INDEX
    Explanations

    conservative, tame, or bland

    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
     flexible
    -0.13
     freely
    -0.12
    antz
    -0.12
     Flexible
    -0.12
     unrestricted
    -0.12
    Flexible
    -0.11
     flexibility
    -0.11
     Chaos
    -0.11
     chaotic
    -0.11
     unlimited
    -0.11
    POSITIVE LOGITS
     conservative
    0.38
     conservatism
    0.31
     wholesome
    0.30
     boring
    0.27
     tame
    0.26
     cautious
    0.26
     sober
    0.25
     Conservative
    0.25
     bland
    0.25
     strict
    0.25
    Activations Density 0.576%

    No Known Activations