© 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. 47262
    Prev
    Next
    INDEX
    Explanations

    ensures quality and makes guarantees

    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
     clandest
    -0.12
    ernes
    -0.10
    UBE
    -0.10
    mmo
    -0.10
    uche
    -0.10
    oria
    -0.10
    ube
    -0.10
    dings
    -0.10
    atten
    -0.10
    andbox
    -0.09
    POSITIVE LOGITS
     unparalleled
    0.17
     ensures
    0.16
     guarantee
    0.16
     ensure
    0.15
     guarantees
    0.15
     ensuring
    0.14
     ensured
    0.14
     delivers
    0.14
     deliver
    0.14
     unmatched
    0.13
    Activations Density 0.284%

    No Known Activations