© 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. 5782
    Prev
    Next
    INDEX
    Explanations

    underestimate / underestimate

    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
     dat
    -0.11
    axes
    -0.11
    vg
    -0.10
    alis
    -0.10
    iba
    -0.10
     disproportionate
    -0.10
    VG
    -0.10
     reasonable
    -0.10
    sp
    -0.09
    867
    -0.09
    POSITIVE LOGITS
     underestimate
    0.25
     underestimated
    0.24
     abilities
    0.13
     capabilities
    0.12
     Intelligence
    0.12
     underst
    0.12
     strength
    0.11
     underrated
    0.11
     intelligence
    0.11
     capacities
    0.10
    Activations Density 0.027%

    No Known Activations