© 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. 30150
    Prev
    Next
    INDEX
    Explanations

    hocken/clique/jukebox/fock

    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
    ÑĬ
    -0.11
    imagin
    -0.10
     conj
    -0.09
    stakes
    -0.09
     dispens
    -0.09
    strup
    -0.09
    modation
    -0.09
     priceless
    -0.09
    apore
    -0.09
     artic
    -0.09
    POSITIVE LOGITS
    strap
    0.16
     Strap
    0.11
    olan
    0.10
     straps
    0.10
    isch
    0.09
    boy
    0.09
    asses
    0.09
    eler
    0.09
    e
    0.09
    eo
    0.09
    Activations Density 0.002%

    No Known Activations