© 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. 17944
    Prev
    Next
    INDEX
    Explanations

    lenovo or elena

    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
    .kr
    -0.09
     tic
    -0.09
     Aurora
    -0.09
     Pitt
    -0.08
     Mol
    -0.08
     plate
    -0.08
    orang
    -0.08
     Rochester
    -0.08
     Cinder
    -0.08
     Zinc
    -0.08
    POSITIVE LOGITS
     Lena
    0.23
    lena
    0.16
     Lenovo
    0.16
     LEN
    0.16
     Nel
    0.13
    .Len
    0.12
     Elena
    0.12
    Len
    0.12
     maxlen
    0.12
     Lens
    0.11
    Activations Density 0.012%

    No Known Activations