© 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. 48532
    Prev
    Next
    INDEX
    Explanations

    numbers after commas

    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
     Dann
    -0.09
     Schwe
    -0.09
    åıĬ
    -0.09
     continu
    -0.08
     mute
    -0.08
    /sign
    -0.08
     Hen
    -0.08
     hitch
    -0.08
     automatically
    -0.08
     cat
    -0.08
    POSITIVE LOGITS
     Cord
    0.11
    éĶĻ
    0.10
     vip
    0.09
     spill
    0.09
     original
    0.09
    Resource
    0.09
    ossa
    0.09
     âĦĸ
    0.09
    SIG
    0.09
     slips
    0.09
    Activations Density 0.004%

    No Known Activations