© 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. 114226
    Prev
    Next
    INDEX
    Explanations

    people come from all over the world

    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
     chast
    -0.09
     Momentum
    -0.09
    Charts
    -0.09
    LF
    -0.08
    ot
    -0.08
     Jun
    -0.08
     Spy
    -0.08
    ACS
    -0.08
    obe
    -0.08
    DFS
    -0.08
    POSITIVE LOGITS
     attracted
    0.18
     pilgrimage
    0.17
     flock
    0.15
     pilgr
    0.15
     converge
    0.15
     attracts
    0.14
     come
    0.14
     attracting
    0.14
     attraction
    0.14
     converged
    0.14
    Activations Density 0.136%

    No Known Activations