© 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. 112335
    Prev
    Next
    INDEX
    Explanations

    prepared carefully, specialized diligently

    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
    .Bottom
    -0.11
    <-
    -0.09
    ĺìĿ´
    -0.09
    ï¿
    -0.09
    âĨIJ
    -0.09
     Deb
    -0.09
     segu
    -0.09
     Knox
    -0.09
    bum
    -0.08
     dav
    -0.08
    POSITIVE LOGITS
     meticulously
    0.23
     carefully
    0.17
     meticulous
    0.16
     **
    0.14
     [âĢ¦]↵↵
    0.13
     tirelessly
    0.13
     strategically
    0.13
     painstaking
    0.12
     boasts
    0.11
     diligently
    0.11
    Activations Density 0.201%

    No Known Activations