© 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. 4654
    Prev
    Next
    INDEX
    Explanations

    register or login

    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
    addon
    -0.09
     nap
    -0.09
     log
    -0.09
     pardon
    -0.09
     provoc
    -0.08
    -du
    -0.08
     bolt
    -0.08
     lod
    -0.08
     login
    -0.08
    íķ
    -0.08
    POSITIVE LOGITS
    ODE
    0.11
    accordion
    0.10
     densities
    0.10
     bull
    0.10
     bulls
    0.09
     ro
    0.09
     Persist
    0.09
     Cart
    0.09
    293
    0.09
    -basket
    0.09
    Activations Density 0.020%

    No Known Activations