© 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. 88692
    Prev
    Next
    INDEX
    Explanations

    verified, selected, sourced 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
    alen
    -0.12
    ambi
    -0.12
     printable
    -0.11
     disguised
    -0.10
    riot
    -0.10
    ronic
    -0.10
     customizable
    -0.10
     larg
    -0.10
     incidental
    -0.10
     iteration
    -0.10
    POSITIVE LOGITS
     sourcing
    0.19
     sourced
    0.18
     curated
    0.14
     vet
    0.13
     proc
    0.13
     carefully
    0.13
     selection
    0.13
     gathering
    0.12
    vet
    0.12
     procurement
    0.12
    Activations Density 0.146%

    No Known Activations