© 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. 116974
    Prev
    Next
    INDEX
    Explanations

    introducing a context or purpose

    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
    ipse
    -0.12
     pony
    -0.11
    oned
    -0.11
    ivant
    -0.10
     Pony
    -0.10
    icap
    -0.10
    ucz
    -0.10
    rame
    -0.10
    Cpp
    -0.10
    deen
    -0.10
    POSITIVE LOGITS
     Lars
    0.09
    getting
    0.09
     LR
    0.08
    Fx
    0.08
    cad
    0.08
     each
    0.08
    (each
    0.07
    Over
    0.07
     exam
    0.07
     Hosp
    0.07
    Activations Density 0.047%

    No Known Activations