© 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. 47939
    Prev
    Next
    INDEX
    Explanations

    a followed by a word

    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
    isti
    -0.10
    zew
    -0.10
    ivi
    -0.09
    redo
    -0.09
    eo
    -0.09
    rary
    -0.09
    aren
    -0.09
    lte
    -0.09
     ...\
    -0.09
    mir
    -0.09
    POSITIVE LOGITS
    .k
    0.25
    /k
    0.14
     renowned
    0.11
     cual
    0.10
     notoriously
    0.10
    ories
    0.10
    .e
    0.10
     former
    0.10
     erst
    0.10
    KA
    0.10
    Activations Density 0.219%

    No Known Activations