© 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. 17637
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers

    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
     decorated
    -0.10
    ³³³³³³³
    -0.08
     canonical
    -0.08
     practically
    -0.08
     enthusiastic
    -0.07
    orf
    -0.07
     positively
    -0.07
     pii
    -0.07
     Serv
    -0.07
    .outputs
    -0.07
    POSITIVE LOGITS
     apro
    0.11
    agged
    0.11
    vo
    0.11
     caveat
    0.11
     reco
    0.11
     freaking
    0.10
    )...
    0.10
     Rid
    0.10
     damned
    0.10
     wilt
    0.10
    Activations Density 0.024%

    No Known Activations