© 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. 116797
    Prev
    Next
    INDEX
    Explanations

    null pointer exception

    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
     Evan
    -0.10
    YYY
    -0.10
     Expansion
    -0.09
     Benton
    -0.09
    uries
    -0.09
     Expedition
    -0.09
     expansive
    -0.09
    alaria
    -0.09
    enza
    -0.09
    )|(
    -0.09
    POSITIVE LOGITS
    bert
    0.13
    sson
    0.13
     desper
    0.12
     damp
    0.11
    PointerException
    0.10
    ius
    0.09
    /false
    0.09
    stell
    0.09
    ivent
    0.09
    adic
    0.08
    Activations Density 0.030%

    No Known Activations