© 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. 17777
    Prev
    Next
    INDEX
    Explanations

    partial endings (-ens, -iens, -nen, -aren, -alen)

    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
    ning
    -0.13
    hin
    -0.11
    inel
    -0.10
    NING
    -0.10
    .glob
    -0.10
    ALLY
    -0.10
    hiro
    -0.10
    iders
    -0.10
    ambre
    -0.10
    itionally
    -0.10
    POSITIVE LOGITS
    o
    0.11
    zial
    0.10
    yi
    0.09
    burg
    0.09
    _partial
    0.08
     Partial
    0.08
    zi
    0.08
     partial
    0.08
    chest
    0.08
    igo
    0.08
    Activations Density 0.198%

    No Known Activations