© 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. 88880
    Prev
    Next
    INDEX
    Explanations

    like this

    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
     arguably
    -0.12
    kin
    -0.09
     Ruf
    -0.09
     misguided
    -0.09
    otas
    -0.09
     might
    -0.09
    maybe
    -0.08
     kend
    -0.08
    itan
    -0.08
    ihan
    -0.08
    POSITIVE LOGITS
     indicating
    0.12
     having
    0.11
     Fountain
    0.11
     showing
    0.10
    rede
    0.10
     affecting
    0.09
     in
    0.09
    agh
    0.09
     remaining
    0.09
     Rede
    0.09
    Activations Density 0.060%

    No Known Activations