© 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. 30321
    Prev
    Next
    INDEX
    Explanations

    to serve or to effect

    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
    anten
    -0.09
    bart
    -0.09
     zug
    -0.09
    ses
    -0.08
    ves
    -0.08
    itag
    -0.08
    vg
    -0.08
    aida
    -0.08
    lay
    -0.08
    claim
    -0.08
    POSITIVE LOGITS
     to
    0.16
     ability
    0.11
    obl
    0.11
     weaken
    0.10
    inox
    0.10
    to
    0.10
     riv
    0.10
     дел
    0.10
     provoke
    0.10
     Gallagher
    0.09
    Activations Density 0.036%

    No Known Activations