© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114835
    Prev
    Next
    INDEX
    Explanations

    cheap, affordable, price, cost

    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
    alta
    -0.09
     caravan
    -0.09
     rect
    -0.09
    Rect
    -0.09
     categorical
    -0.08
     Olympics
    -0.08
     gloss
    -0.08
    getto
    -0.08
     Rect
    -0.08
    epam
    -0.08
    POSITIVE LOGITS
     Prostit
    0.10
     cheerful
    0.10
    Cheap
    0.10
     impover
    0.09
     Cheap
    0.09
    mouseup
    0.09
     expend
    0.09
     directed
    0.09
     cheapest
    0.08
     labor
    0.08
    Activations Density 0.074%

    No Known Activations