© 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. 28920
    Prev
    Next
    INDEX
    Explanations

    brush borders

    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
    ruk
    -0.12
    asz
    -0.11
    ivot
    -0.10
    lyn
    -0.10
     Dag
    -0.10
    оÑģÑĤи
    -0.10
     DAG
    -0.10
    adel
    -0.10
    iswa
    -0.10
     Geoffrey
    -0.10
    POSITIVE LOGITS
     waiting
    0.12
     ready
    0.12
     gates
    0.10
     hes
    0.10
     doorstep
    0.10
     inviting
    0.10
     poised
    0.10
     Waiting
    0.10
     begging
    0.09
     refusing
    0.09
    Activations Density 0.009%

    No Known Activations