© 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. 50507
    Prev
    Next
    INDEX
    Explanations

    treated separately

    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
     todd
    -0.12
    gee
    -0.11
     moy
    -0.11
     separately
    -0.11
    gie
    -0.11
    yah
    -0.11
     Moy
    -0.11
    tant
    -0.11
     sized
    -0.11
     VECTOR
    -0.11
    POSITIVE LOGITS
    onga
    0.08
     dug
    0.07
    mant
    0.07
     trending
    0.07
     Kenn
    0.07
     multid
    0.07
     predecessors
    0.07
     unreal
    0.07
    ces
    0.07
     mot
    0.06
    Activations Density 0.001%

    No Known Activations