© 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. 7187
    Prev
    Next
    INDEX
    Explanations

    discover and understand self or purpose

    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
     vet
    -0.10
     Warn
    -0.10
     provocative
    -0.09
    -io
    -0.09
    /io
    -0.09
     provoke
    -0.09
    educt
    -0.09
    ARAM
    -0.09
     exclus
    -0.09
    .codes
    -0.09
    POSITIVE LOGITS
     redis
    0.27
     discovering
    0.25
     discover
    0.25
     discovery
    0.24
     Discover
    0.22
     self
    0.21
     SELF
    0.21
     discovers
    0.20
     Self
    0.20
     discovered
    0.19
    Activations Density 0.078%

    No Known Activations