© 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. 18076
    Prev
    Next
    INDEX
    Explanations

    first point or new section

    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
     eta
    -0.09
    OLON
    -0.09
     ir
    -0.09
     Hund
    -0.09
     pond
    -0.08
     Potter
    -0.08
     it
    -0.08
    hana
    -0.08
    olon
    -0.08
    hud
    -0.07
    POSITIVE LOGITS
     Firstly
    0.27
     Here
    0.24
     firstly
    0.23
    Here
    0.22
     here
    0.22
    First
    0.19
     Below
    0.18
     First
    0.18
    é¦ĸ
    0.18
    .First
    0.18
    Activations Density 0.141%

    No Known Activations