© 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. 30144
    Prev
    Next
    INDEX
    Explanations

    scar, links, lock, consult

    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
     mutual
    -0.09
     Shack
    -0.09
     ourselves
    -0.09
     organised
    -0.09
     joint
    -0.09
    RING
    -0.09
    ades
    -0.09
     climbing
    -0.08
     hust
    -0.08
    ross
    -0.08
    POSITIVE LOGITS
     grip
    0.12
     reflex
    0.12
     tightly
    0.12
     grips
    0.11
     invol
    0.11
     defensively
    0.11
     gripping
    0.11
     embrace
    0.10
     gri
    0.10
     suck
    0.10
    Activations Density 0.005%

    No Known Activations