© 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. 15581
    Prev
    Next
    INDEX
    Explanations

    difficulty

    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
     Wish
    -0.09
     Sig
    -0.09
     Wat
    -0.09
     freely
    -0.09
     lawful
    -0.08
     head
    -0.08
    BP
    -0.08
     Tay
    -0.08
     Cra
    -0.08
     indulge
    -0.08
    POSITIVE LOGITS
    -to
    0.14
     harder
    0.13
     hardest
    0.12
     uphill
    0.12
    -core
    0.12
    /fr
    0.12
     transitions
    0.12
    -hard
    0.12
    /im
    0.12
     tasks
    0.12
    Activations Density 0.110%

    No Known Activations