© 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. 48338
    Prev
    Next
    INDEX
    Explanations

    these partial those example

    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
     â
    -0.15
    ÃĤ
    -0.13
    â
    -0.13
     &#
    -0.12
    &#
    -0.12
    âĢİ
    -0.11
    âĢ
    -0.11
    âĢŀ
    -0.10
    âĢIJ
    -0.09
     âĢŀ
    -0.09
    POSITIVE LOGITS
     aforementioned
    0.11
    eron
    0.10
     afore
    0.09
    eros
    0.08
    ago
    0.08
    nim
    0.08
     ^↵
    0.07
    .Focused
    0.07
    ',↵↵
    0.07
    ко
    0.07
    Activations Density 4.774%

    No Known Activations