© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6434
    Prev
    Next
    INDEX
    Explanations

    they've done something

    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
     myself
    -0.10
     momentarily
    -0.10
     regularly
    -0.09
     temporarily
    -0.09
    /session
    -0.09
     Cooperative
    -0.09
    Tonight
    -0.09
     spontaneously
    -0.09
     your
    -0.08
     Owned
    -0.08
    POSITIVE LOGITS
     designers
    0.20
     design
    0.17
     designing
    0.17
    design
    0.16
     sacrificed
    0.14
    设计
    0.14
     chose
    0.14
     inclusion
    0.14
     incorporated
    0.13
     opted
    0.13
    Activations Density 0.807%

    No Known Activations