© 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. 7833
    Prev
    Next
    INDEX
    Explanations

    in accordance with

    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
    rc
    -0.10
     Tx
    -0.10
    illi
    -0.10
     pragmatic
    -0.10
    qu
    -0.09
     Honour
    -0.09
     precaution
    -0.09
     Hon
    -0.09
     Pall
    -0.09
    bet
    -0.09
    POSITIVE LOGITS
    Forge
    0.10
     accordance
    0.09
     atmos
    0.09
    sal
    0.09
    SDL
    0.09
    Baby
    0.09
     rooms
    0.08
     Carry
    0.08
     licensed
    0.08
     Lov
    0.08
    Activations Density 0.002%

    No Known Activations