© 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. 27831
    Prev
    Next
    INDEX
    Explanations

    uncertainty or incompleteness

    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
    -La
    -0.11
     Teh
    -0.11
     nomin
    -0.11
    vil
    -0.10
     shortened
    -0.09
     Ramp
    -0.09
     CMP
    -0.09
     cin
    -0.09
     Ivanka
    -0.09
    535
    -0.09
    POSITIVE LOGITS
     incapable
    0.17
     unsure
    0.17
     immature
    0.14
     unreliable
    0.14
     unclear
    0.14
     desperate
    0.13
     unstable
    0.13
     unwilling
    0.13
     lacks
    0.13
     insecure
    0.13
    Activations Density 0.009%

    No Known Activations