© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6319
    Prev
    Next
    INDEX
    Explanations

    read more

    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
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.10
    ÑĢÑĥк
    -0.10
    .appspot
    -0.10
     quat
    -0.10
    Merit
    -0.10
    \:
    -0.09
     Twice
    -0.09
    ral
    -0.09
    ruk
    -0.09
    rang
    -0.09
    POSITIVE LOGITS
     Hoy
    0.09
     Peters
    0.09
    haul
    0.09
    gos
    0.09
     standby
    0.09
     HERE
    0.08
    avs
    0.08
     spec
    0.08
    piel
    0.08
     externally
    0.08
    Activations Density 0.006%

    No Known Activations