© 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. 113868
    Prev
    Next
    INDEX
    Explanations

    state or completion

    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
    âĢ¦
    -0.09
     Mitch
    -0.08
    rah
    -0.08
    olo
    -0.08
     tossed
    -0.08
     however
    -0.08
    âĢ¦and
    -0.07
     ought
    -0.07
     midd
    -0.07
     Pres
    -0.07
    POSITIVE LOGITS
     iota
    0.11
    acas
    0.11
    rames
    0.10
    êµ
    0.10
     McD
    0.10
    avery
    0.10
     urgently
    0.10
    coni
    0.10
     gerne
    0.10
    ropol
    0.10
    Activations Density 0.260%

    No Known Activations