© 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. 46669
    Prev
    Next
    INDEX
    Explanations

    loosening, worsening

    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
    ston
    -0.12
     McCabe
    -0.11
    UTES
    -0.11
     crush
    -0.11
    es
    -0.11
    RITE
    -0.11
    ba
    -0.10
    -La
    -0.10
    chron
    -0.10
    odom
    -0.10
    POSITIVE LOGITS
    ening
    0.22
    ened
    0.21
    ely
    0.13
     loos
    0.12
    ens
    0.12
    ily
    0.11
    eness
    0.10
    lama
    0.09
    eners
    0.09
    ener
    0.09
    Activations Density 0.001%

    No Known Activations