© 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. 47745
    Prev
    Next
    INDEX
    Explanations

    practice and experimentation

    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
     interact
    -0.12
     arrivals
    -0.11
     interacting
    -0.11
     hugged
    -0.10
    Interaction
    -0.10
     sympathy
    -0.10
    adr
    -0.10
    OOSE
    -0.10
     Fork
    -0.09
     interacts
    -0.09
    POSITIVE LOGITS
     implementation
    0.14
     Implementation
    0.14
     reluct
    0.13
     consent
    0.13
     experimentation
    0.13
     prepar
    0.13
    Implementation
    0.13
     Experiment
    0.13
    Experiment
    0.12
     enthusiasm
    0.12
    Activations Density 0.168%

    No Known Activations