© 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. 28818
    Prev
    Next
    INDEX
    Explanations

    Chang, Narashima, davana

    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
    /Dk
    -0.14
     tamp
    -0.11
     tq
    -0.10
     scar
    -0.10
     jt
    -0.10
    ÅĤad
    -0.10
     stav
    -0.10
    à¸ģร
    -0.10
     Paz
    -0.10
    wdx
    -0.10
    POSITIVE LOGITS
    enza
    0.08
    !(
    0.08
     omin
    0.07
    oreach
    0.07
    !</
    0.07
     magna
    0.07
    coc
    0.07
    wahl
    0.07
    umpt
    0.07
     jego
    0.07
    Activations Density 0.180%

    No Known Activations