© 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. 26495
    Prev
    Next
    INDEX
    Explanations

    strategic operational

    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
     tr
    -0.08
     altern
    -0.07
    agens
    -0.07
    amel
    -0.07
     tran
    -0.07
    agen
    -0.07
    wis
    -0.07
    icken
    -0.06
     specialized
    -0.06
    stre
    -0.06
    POSITIVE LOGITS
     undoubtedly
    0.14
    Uvs
    0.13
     looph
    0.13
     resultant
    0.13
     irrespective
    0.13
     Pais
    0.12
     debunk
    0.12
     gala
    0.12
     loophole
    0.12
    IFn
    0.11
    Activations Density 0.002%

    No Known Activations