© 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. 50364
    Prev
    Next
    INDEX
    Explanations

    requested or desired items

    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
    andes
    -0.09
    anus
    -0.08
     Sidd
    -0.07
    ipi
    -0.07
    anth
    -0.07
    eco
    -0.07
    angu
    -0.07
     Barth
    -0.07
    eyer
    -0.07
     nerves
    -0.07
    POSITIVE LOGITS
     promised
    0.53
     desired
    0.44
     requested
    0.43
     hoped
    0.35
     sought
    0.33
    requested
    0.32
    desired
    0.32
     required
    0.31
     Desired
    0.31
     demanded
    0.30
    Activations Density 0.363%

    No Known Activations