© 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. 116317
    Prev
    Next
    INDEX
    Explanations

    horsepower rating

    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
     handed
    -0.09
    ewith
    -0.08
     Microwave
    -0.08
    ias
    -0.08
     Oliveira
    -0.07
     Nichols
    -0.07
    PMC
    -0.07
     bd
    -0.07
    aine
    -0.07
     Coll
    -0.07
    POSITIVE LOGITS
     rating
    0.12
    aban
    0.11
     Rating
    0.11
     ratings
    0.11
     Throne
    0.11
    judge
    0.10
     hamm
    0.10
    _hor
    0.10
    rob
    0.10
    -rating
    0.10
    Activations Density 0.002%

    No Known Activations