© 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. 31634
    Prev
    Next
    INDEX
    Explanations

    states of being or readiness

    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
    olen
    -0.09
     tempting
    -0.09
     contro
    -0.09
     Uns
    -0.08
    ta
    -0.08
    es
    -0.08
    elm
    -0.08
    enta
    -0.08
     stabil
    -0.08
    fila
    -0.08
    POSITIVE LOGITS
     unable
    0.24
     able
    0.24
     willing
    0.21
     aware
    0.20
     afraid
    0.20
     ready
    0.20
    unable
    0.18
     incapable
    0.16
    ready
    0.15
     eager
    0.14
    Activations Density 0.251%

    No Known Activations