© 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. 90073
    Prev
    Next
    INDEX
    Explanations

    lists separated by and or ,

    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
    hra
    -0.09
    eo
    -0.09
    eries
    -0.08
    [number
    -0.08
     Walton
    -0.08
    ellery
    -0.08
    odash
    -0.08
     NRA
    -0.08
    \/
    -0.08
    "d
    -0.08
    POSITIVE LOGITS
    enger
    0.12
    rone
    0.10
    inde
    0.09
    isy
    0.09
     HIM
    0.09
    ef
    0.09
     testim
    0.08
    iping
    0.08
    fee
    0.08
    pest
    0.08
    Activations Density 0.649%

    No Known Activations