© 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. 33012
    Prev
    Next
    INDEX
    Explanations

    partial followed by context

    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
     Bark
    -0.09
     Fist
    -0.09
     Dios
    -0.08
    nad
    -0.08
    ande
    -0.08
     Banc
    -0.08
    abad
    -0.08
    enco
    -0.08
    nia
    -0.08
    usc
    -0.08
    POSITIVE LOGITS
    ity
    0.19
    /full
    0.16
    ities
    0.16
     partial
    0.16
     Partial
    0.15
    .partial
    0.14
    ITY
    0.14
    Partial
    0.14
    mente
    0.14
     nudity
    0.12
    Activations Density 0.084%

    No Known Activations