© 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. 115652
    Prev
    Next
    INDEX
    Explanations

    have been reported/used/verified

    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
    ting
    -0.07
    mani
    -0.07
    osti
    -0.07
     Destruction
    -0.07
     multiples
    -0.07
    ising
    -0.07
    andon
    -0.07
     aided
    -0.07
    mond
    -0.07
     hast
    -0.06
    POSITIVE LOGITS
     proven
    0.14
     shown
    0.14
    rag
    0.13
     Fem
    0.11
    entic
    0.11
     Kle
    0.11
     scientifically
    0.10
     clinically
    0.10
    hp
    0.10
    å»
    0.10
    Activations Density 0.016%

    No Known Activations