© 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. 48340
    Prev
    Next
    INDEX
    Explanations

    I know, I want, I think

    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
     participates
    -0.11
     accompanies
    -0.11
     trusting
    -0.11
     succ
    -0.11
    IAS
    -0.10
    trying
    -0.10
     Richardson
    -0.10
     accompany
    -0.10
     defends
    -0.10
    agh
    -0.10
    POSITIVE LOGITS
     pity
    0.11
     SA
    0.09
    âĢİ
    0.09
     warned
    0.09
     mercy
    0.09
     decided
    0.09
     âĢİ
    0.09
     disappointment
    0.09
     bet
    0.09
     WARN
    0.09
    Activations Density 0.024%

    No Known Activations