© 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. 113346
    Prev
    Next
    INDEX
    Explanations

    United States Court of Appeals Ninth Circuit

    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
     ready
    -0.10
     dedic
    -0.09
     Parcel
    -0.09
    allen
    -0.09
     Preparation
    -0.08
     prepar
    -0.08
    zac
    -0.08
     medi
    -0.08
     preparations
    -0.08
     Sparks
    -0.08
    POSITIVE LOGITS
     cautiously
    0.15
     complied
    0.13
     curiosity
    0.13
     hes
    0.13
     cautious
    0.13
    Entering
    0.12
     obed
    0.12
    joining
    0.12
     Follow
    0.12
     suspicion
    0.11
    Activations Density 0.022%

    No Known Activations