© 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. 30922
    Prev
    Next
    INDEX
    Explanations

    .Start, commissioned, As, to, Memory, if

    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
     Flint
    -0.10
    adesh
    -0.08
     intr
    -0.07
    da
    -0.07
     intercept
    -0.07
     requis
    -0.07
     electrom
    -0.07
     volum
    -0.07
     slag
    -0.07
     Messenger
    -0.07
    POSITIVE LOGITS
     Bei
    0.15
     intolerance
    0.12
    Bei
    0.11
     Historic
    0.11
     Mik
    0.11
    Montserrat
    0.11
     Til
    0.10
    AZE
    0.10
    );;↵
    0.10
     Ari
    0.10
    Activations Density 0.105%

    No Known Activations