© 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. 16938
    Prev
    Next
    INDEX
    Explanations

    belonging to

    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
    heimer
    -0.10
     Auditor
    -0.09
    upe
    -0.09
     grading
    -0.09
     auditor
    -0.08
    azio
    -0.08
     predecessor
    -0.08
    chio
    -0.08
    jian
    -0.08
     upstream
    -0.08
    POSITIVE LOGITS
     belonged
    0.29
     belongs
    0.29
     belong
    0.28
    belongs
    0.21
     belonging
    0.19
     reserved
    0.19
     attributed
    0.18
     awarded
    0.18
     allocated
    0.17
     vested
    0.17
    Activations Density 0.663%

    No Known Activations