© 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. 33109
    Prev
    Next
    INDEX
    Explanations

    it is or it,

    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
    emb
    -0.10
     abund
    -0.09
     straight
    -0.09
    legate
    -0.09
     Pit
    -0.09
    velt
    -0.09
     semi
    -0.09
     Sno
    -0.09
     dik
    -0.09
    haus
    -0.09
    POSITIVE LOGITS
     happening
    0.11
    estro
    0.11
     occurring
    0.08
    eni
    0.08
    Lon
    0.08
     dumps
    0.08
     Aston
    0.08
    tera
    0.08
    ici
    0.08
    aly
    0.08
    Activations Density 0.040%

    No Known Activations