© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32050
    Prev
    Next
    INDEX
    Explanations

    want to

    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
    anza
    -0.10
     tighten
    -0.10
     rever
    -0.10
     lone
    -0.09
    atten
    -0.09
     co
    -0.09
    358
    -0.09
     LDL
    -0.08
    aint
    -0.08
     refrain
    -0.08
    POSITIVE LOGITS
     More
    0.14
    æĽ´
    0.14
     more
    0.13
     MORE
    0.13
    more
    0.12
     Want
    0.12
    More
    0.11
     mehr
    0.11
     happier
    0.11
    isis
    0.11
    Activations Density 0.014%

    No Known Activations