© 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. 30220
    Prev
    Next
    INDEX
    Explanations

    come or hurry

    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
    ocha
    -0.10
    .shtml
    -0.09
    ock
    -0.08
    acco
    -0.08
    (Self
    -0.08
    anos
    -0.08
     Cha
    -0.07
     dumpster
    -0.07
    lich
    -0.07
     midd
    -0.07
    POSITIVE LOGITS
     Come
    0.22
    Come
    0.21
     hurry
    0.20
    come
    0.20
     come
    0.20
     Hur
    0.18
     coax
    0.15
    COME
    0.15
     c
    0.15
     hur
    0.15
    Activations Density 0.047%

    No Known Activations