© 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. 46888
    Prev
    Next
    INDEX
    Explanations

    council for, on, of, candidate

    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
    imals
    -0.08
    cano
    -0.08
     Carnival
    -0.08
    emb
    -0.08
    jes
    -0.08
    alam
    -0.08
    bs
    -0.08
     embar
    -0.07
    shaw
    -0.07
     coinc
    -0.07
    POSITIVE LOGITS
    ors
    0.21
    or
    0.13
    woman
    0.13
    member
    0.13
    .hy
    0.12
    members
    0.12
     chambers
    0.11
    -manager
    0.11
    oley
    0.11
    oric
    0.11
    Activations Density 0.046%

    No Known Activations