© 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. 7770
    Prev
    Next
    INDEX
    Explanations

    changing course

    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
     Hatch
    -0.09
    atten
    -0.08
    abet
    -0.08
    ute
    -0.08
    esen
    -0.08
    esi
    -0.08
     Vor
    -0.08
    /archive
    -0.07
    onde
    -0.07
     ren
    -0.07
    POSITIVE LOGITS
     meanwhile
    0.14
     thereby
    0.13
     eventually
    0.12
     hopefully
    0.12
     perhaps
    0.12
     afterward
    0.11
     dabei
    0.10
     moreover
    0.10
     both
    0.10
     thereafter
    0.10
    Activations Density 0.241%

    No Known Activations