© 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. 32337
    Prev
    Next
    INDEX
    Explanations

    price and discount information

    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
    Nation
    -0.08
     moderately
    -0.08
     Dorm
    -0.08
    ERM
    -0.08
    \e
    -0.07
    cec
    -0.07
    hec
    -0.07
    tering
    -0.07
     fallout
    -0.07
    ove
    -0.07
    POSITIVE LOGITS
     sale
    0.12
     Blanco
    0.12
     reduced
    0.11
    اØ
    0.11
     slicing
    0.11
     Rodrig
    0.11
     IllegalAccessException
    0.11
    inan
    0.11
    /validation
    0.10
     negotiated
    0.10
    Activations Density 0.039%

    No Known Activations