© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7417
    Prev
    Next
    INDEX
    Explanations

    states of hardship or deficiency

    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
     due
    -0.14
     via
    -0.12
     based
    -0.10
     Hol
    -0.10
     through
    -0.10
    _due
    -0.10
    due
    -0.09
     Due
    -0.09
     Cory
    -0.09
    Due
    -0.09
    POSITIVE LOGITS
     alone
    0.18
    alone
    0.16
     Alone
    0.15
     combined
    0.15
     coupled
    0.11
    combined
    0.11
     overload
    0.11
    atism
    0.10
     sheer
    0.10
    oden
    0.10
    Activations Density 0.440%

    No Known Activations