© 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. 48717
    Prev
    Next
    INDEX
    Explanations

    code and command prompts

    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
    FAQ
    -0.08
    221
    -0.08
    oya
    -0.08
    Conflict
    -0.08
     overhead
    -0.07
     misleading
    -0.07
    %^
    -0.07
    inka
    -0.07
     blame
    -0.07
    Jur
    -0.07
    POSITIVE LOGITS
     Explicit
    0.11
     deferred
    0.11
     RECT
    0.11
    uesta
    0.10
     responses
    0.10
     replies
    0.10
    =response
    0.10
    ?"↵↵↵↵
    0.10
    ."↵↵↵↵
    0.10
     tink
    0.10
    Activations Density 0.035%

    No Known Activations