© 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. 17322
    Prev
    Next
    INDEX
    Explanations

    a number 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
     Ces
    -0.08
    ège
    -0.07
    ocha
    -0.07
     saw
    -0.07
    rete
    -0.07
    dsl
    -0.07
    bote
    -0.07
    bench
    -0.07
     shall
    -0.06
    inish
    -0.06
    POSITIVE LOGITS
     plethora
    0.16
     few
    0.16
     variety
    0.15
     multitude
    0.15
     myriad
    0.15
    vari
    0.14
     handful
    0.14
     number
    0.14
     Few
    0.14
     couple
    0.13
    Activations Density 0.008%

    No Known Activations