© 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. 5226
    Prev
    Next
    INDEX
    Explanations

    more details or options

    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
     con
    -0.11
    rep
    -0.10
    .at
    -0.09
    Atlas
    -0.09
     McL
    -0.09
    atten
    -0.09
    UES
    -0.08
     cá
    -0.08
    voy
    -0.08
    lds
    -0.08
    POSITIVE LOGITS
     Kata
    0.11
     sting
    0.09
     advis
    0.09
     Hav
    0.09
     upt
    0.09
    oref
    0.09
    OldData
    0.08
    emin
    0.08
    .gb
    0.08
     bom
    0.08
    Activations Density 0.008%

    No Known Activations