© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113991
    Prev
    Next
    INDEX
    Explanations

    safety and technical solutions

    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
    uta
    -0.10
    irim
    -0.10
     ~(
    -0.09
     Conc
    -0.09
     upt
    -0.09
    odor
    -0.09
    bed
    -0.09
    ync
    -0.09
    orton
    -0.09
    orts
    -0.09
    POSITIVE LOGITS
     kisses
    0.10
     against
    0.09
     palms
    0.09
    elter
    0.09
     Against
    0.09
    against
    0.09
     Leer
    0.09
     orbs
    0.09
     hands
    0.08
     sensation
    0.08
    Activations Density 0.011%

    No Known Activations