© 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. 17597
    Prev
    Next
    INDEX
    Explanations

    which of

    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
    aco
    -0.10
    (Some
    -0.09
    ĶåĽŀ
    -0.09
     Instances
    -0.09
    iego
    -0.09
    benchmark
    -0.09
    ãĤ§
    -0.09
    UTE
    -0.09
     belong
    -0.09
    .rs
    -0.09
    POSITIVE LOGITS
    mia
    0.10
    icha
    0.08
     myriad
    0.08
     predic
    0.08
     cour
    0.08
     casc
    0.08
    rias
    0.07
    ]][
    0.07
    vel
    0.07
    imon
    0.07
    Activations Density 0.014%

    No Known Activations