© 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. 31632
    Prev
    Next
    INDEX
    Explanations

    experimental report influence

    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
     repe
    -0.10
     Rede
    -0.09
     complaints
    -0.09
     Complaint
    -0.09
     epidemi
    -0.08
     vault
    -0.08
     ante
    -0.08
     gross
    -0.08
     Stall
    -0.08
     descriptors
    -0.08
    POSITIVE LOGITS
     experiment
    0.20
     Experiment
    0.18
    Experiment
    0.17
     Implicit
    0.16
     prim
    0.16
     primes
    0.16
     experimental
    0.16
     stereotype
    0.15
     experiments
    0.15
     bystand
    0.15
    Activations Density 1.338%

    No Known Activations