© 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. 47368
    Prev
    Next
    INDEX
    Explanations

    Sir Jonathan, Barry, Daniel

    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
    elia
    -0.09
    dale
    -0.09
    erin
    -0.08
    lp
    -0.08
    798
    -0.08
          ↵      ↵
    -0.08
    ENDOR
    -0.08
     Hag
    -0.08
     Sabb
    -0.08
     quot
    -0.08
    POSITIVE LOGITS
    rah
    0.14
    ius
    0.13
    ships
    0.12
    iously
    0.11
    ship
    0.11
    nex
    0.11
    ree
    0.10
     Geoffrey
    0.10
    hc
    0.10
    itation
    0.10
    Activations Density 0.009%

    No Known Activations