© 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. 15000
    Prev
    Next
    INDEX
    Explanations

    I am building a model

    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
    owa
    -0.09
     collects
    -0.09
     Collect
    -0.09
     bri
    -0.09
     collect
    -0.09
     collected
    -0.09
     unanswered
    -0.09
     secre
    -0.09
    Leg
    -0.08
     pinch
    -0.08
    POSITIVE LOGITS
     adopt
    0.17
     adopted
    0.17
     adopts
    0.14
     adopting
    0.14
     Adopt
    0.14
    adopt
    0.13
     adher
    0.13
     belonged
    0.13
    éĩ
    0.13
     belong
    0.12
    Activations Density 0.232%

    No Known Activations