© 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. 16867
    Prev
    Next
    INDEX
    Explanations

    being in

    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
    749
    -0.09
    539
    -0.09
    onto
    -0.09
    agar
    -0.08
     whom
    -0.08
     extrapol
    -0.08
    743
    -0.08
     cap
    -0.08
    -cap
    -0.08
     break
    -0.08
    POSITIVE LOGITS
    ducted
    0.13
     forthcoming
    0.10
    iesel
    0.10
    arded
    0.10
     presence
    0.10
     control
    0.10
    /manage
    0.09
    /control
    0.09
     Trinity
    0.09
     touch
    0.09
    Activations Density 0.048%

    No Known Activations