© 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. 47207
    Prev
    Next
    INDEX
    Explanations

    name assignments

    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
    erness
    -0.09
    mans
    -0.09
    ï¼ģ↵↵
    -0.08
     Grimm
    -0.08
     soaked
    -0.08
    );↵↵
    -0.08
     "↵↵
    -0.08
    CEL
    -0.08
     Loader
    -0.08
     =↵↵
    -0.08
    POSITIVE LOGITS
     undisclosed
    0.14
    lien
    0.12
    ammu
    0.10
    lover
    0.10
     unspecified
    0.10
    Unnamed
    0.10
    ensual
    0.09
     alias
    0.09
    (alias
    0.09
     ##↵
    0.09
    Activations Density 0.002%

    No Known Activations