© 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. 5697
    Prev
    Next
    INDEX
    Explanations

    thermal transferPower suppliesGlass splashbacksdistanceillary electrophoresisaerobic fitness

    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
     provid
    -0.09
    eroon
    -0.08
     vitae
    -0.08
     reco
    -0.08
    olson
    -0.08
     Lockheed
    -0.07
     unmist
    -0.07
     incor
    -0.07
     Soc
    -0.07
     eyeb
    -0.07
    POSITIVE LOGITS
     (/
    0.13
    GAN
    0.11
    -related
    0.11
     vs
    0.11
    &amp
    0.11
    ::.
    0.11
    Ä°
    0.11
    :w
    0.11
    .dll
    0.10
    777
    0.10
    Activations Density 1.772%

    No Known Activations