© 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. 116141
    Prev
    Next
    INDEX
    Explanations

    orchestra or orchard

    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
     Cruc
    -0.10
     Burr
    -0.09
    âĶĢâĶĢ
    -0.08
    atte
    -0.08
    åĪ«
    -0.08
     punct
    -0.08
     superficial
    -0.08
     stere
    -0.08
     wart
    -0.08
    igest
    -0.08
    POSITIVE LOGITS
     orch
    0.13
    estr
    0.13
    urally
    0.11
    loff
    0.11
    itecture
    0.11
    ral
    0.11
     orchest
    0.10
    ration
    0.10
    yd
    0.10
     Orch
    0.10
    Activations Density 0.027%

    No Known Activations