© 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. 27114
    Prev
    Next
    INDEX
    Explanations

    too

    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
     apl
    -0.11
    lec
    -0.11
    erin
    -0.08
     aup
    -0.08
     bach
    -0.08
    eding
    -0.08
     Twins
    -0.08
    Č↵
    -0.08
    iber
    -0.08
     Germ
    -0.08
    POSITIVE LOGITS
     Too
    0.24
    Too
    0.24
    /to
    0.24
     too
    0.23
    too
    0.22
    -too
    0.21
     TOO
    0.20
     demasi
    0.13
    å¤
    0.13
     insufficient
    0.13
    Activations Density 0.129%

    No Known Activations