© 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. 15173
    Prev
    Next
    INDEX
    Explanations

    fastening things together

    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
     Suz
    -0.08
    sume
    -0.07
     negot
    -0.07
    hra
    -0.07
     dint
    -0.07
    comed
    -0.07
     creep
    -0.07
     nud
    -0.06
     kept
    -0.06
    sj
    -0.06
    POSITIVE LOGITS
     tightly
    0.23
     firmly
    0.23
     securely
    0.22
     tighter
    0.22
     together
    0.20
     tight
    0.20
     onto
    0.20
     Tight
    0.17
    åĪ°
    0.17
     Together
    0.17
    Activations Density 0.194%

    No Known Activations