© 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. 90371
    Prev
    Next
    INDEX
    Explanations

    connect the dots

    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
     reassuring
    -0.09
     disagreed
    -0.09
    ali
    -0.08
     postfix
    -0.08
     ali
    -0.08
    _appro
    -0.08
    alice
    -0.08
    Appro
    -0.08
     faker
    -0.08
     disagreements
    -0.07
    POSITIVE LOGITS
     connecting
    0.40
     dots
    0.38
     connect
    0.38
     Connecting
    0.37
     connects
    0.37
    Connecting
    0.35
     connections
    0.33
    connecting
    0.32
     Connect
    0.32
    -connect
    0.31
    Activations Density 0.286%

    No Known Activations