© 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. 114080
    Prev
    Next
    INDEX
    Explanations

    after punctuation or "well", "on", "in", "the"

    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
     she
    -0.51
    å¥
    -0.47
     her
    -0.46
    she
    -0.44
     hers
    -0.41
    She
    -0.40
     She
    -0.38
    .She
    -0.38
     herself
    -0.36
    her
    -0.29
    POSITIVE LOGITS
    ieber
    0.08
     Kab
    0.07
    aira
    0.07
     ma
    0.07
    -controls
    0.07
    386
    0.07
     ellos
    0.07
     Honey
    0.07
    stm
    0.07
    Versions
    0.07
    Activations Density 0.078%

    No Known Activations