© 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. 89990
    Prev
    Next
    INDEX
    Explanations

    universe, worlds, places, anywhere

    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
     sinking
    -0.10
     reg
    -0.10
    -columns
    -0.10
     lev
    -0.10
     Casa
    -0.10
     underwater
    -0.09
     Followers
    -0.09
     social
    -0.09
     subst
    -0.09
    _station
    -0.09
    POSITIVE LOGITS
     universe
    0.39
     univers
    0.38
     Universe
    0.35
     Univers
    0.28
     worlds
    0.24
     mult
    0.23
     cosmos
    0.23
    Univers
    0.23
     Mult
    0.21
    iverse
    0.21
    Activations Density 0.286%

    No Known Activations