© 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. 31419
    Prev
    Next
    INDEX
    Explanations

    ongoing actions or states

    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
     knowing
    -0.14
     differing
    -0.13
    ignment
    -0.11
    ownership
    -0.11
     eventual
    -0.10
     attempted
    -0.10
     belonging
    -0.10
     failed
    -0.10
     escaped
    -0.10
     owning
    -0.10
    POSITIVE LOGITS
     able
    0.24
     aware
    0.20
     gonna
    0.19
     afraid
    0.17
     unable
    0.17
     asleep
    0.16
     doing
    0.16
     supposed
    0.15
     trying
    0.15
     going
    0.15
    Activations Density 0.191%

    No Known Activations