© 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. 18045
    Prev
    Next
    INDEX
    Explanations

    ensure even coverage

    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
    upo
    -0.10
     diverted
    -0.10
     typealias
    -0.10
    uits
    -0.10
     fists
    -0.09
     compagn
    -0.09
     acomp
    -0.09
     frustr
    -0.09
    contri
    -0.09
    -NLS
    -0.09
    POSITIVE LOGITS
     unreachable
    0.24
     corners
    0.22
     inaccessible
    0.22
     areas
    0.21
     coverage
    0.20
     Areas
    0.20
     missed
    0.19
     Coverage
    0.19
     thorough
    0.18
     reachable
    0.17
    Activations Density 0.328%

    No Known Activations