© 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. 88139
    Prev
    Next
    INDEX
    Explanations

    bonus tracks

    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
     Mog
    -0.10
    agli
    -0.09
     Mall
    -0.09
    vida
    -0.09
    VIP
    -0.09
    ucz
    -0.09
    edd
    -0.08
     mog
    -0.08
    uis
    -0.08
    sem
    -0.08
    POSITIVE LOGITS
     dam
    0.11
     ens
    0.10
     Ramp
    0.10
     Burl
    0.10
     Plat
    0.10
     Fun
    0.10
     AAA
    0.09
    rn
    0.09
    Stuff
    0.09
     Ihr
    0.09
    Activations Density 0.001%

    No Known Activations