© 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. 88058
    Prev
    Next
    INDEX
    Explanations

    ai followed by word parts

    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
     accom
    -0.09
    -placement
    -0.09
    opes
    -0.09
    INGTON
    -0.09
     substant
    -0.09
    ukes
    -0.09
     HQ
    -0.08
    INY
    -0.08
    kes
    -0.08
    acro
    -0.08
    POSITIVE LOGITS
     Consolid
    0.10
     Gilles
    0.09
     Overse
    0.09
    нов
    0.09
    usting
    0.09
    ì¹ĺ
    0.09
    dia
    0.09
    arov
    0.08
    rial
    0.08
    nist
    0.08
    Activations Density 0.266%

    No Known Activations