© 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. 32461
    Prev
    Next
    INDEX
    Explanations

    links and lists

    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
    inho
    -0.10
    coli
    -0.09
    ofday
    -0.09
    pong
    -0.09
     SND
    -0.09
    kich
    -0.08
    isque
    -0.08
    euillez
    -0.08
    ndl
    -0.08
    §Ãĥ
    -0.08
    POSITIVE LOGITS
     incom
    0.09
     omn
    0.09
     Yi
    0.09
    [list
    0.09
    [source
    0.09
     wearable
    0.09
    >manual
    0.08
     bor
    0.08
     middleware
    0.08
    erti
    0.08
    Activations Density 0.463%

    No Known Activations