© 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. 27538
    Prev
    Next
    INDEX
    Explanations

    confirming or rejecting

    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
    uong
    -0.11
     Kü
    -0.10
     bunk
    -0.10
    rov
    -0.09
    slick
    -0.09
     Kling
    -0.09
    ocking
    -0.09
     needless
    -0.09
    Forbidden
    -0.09
     pornos
    -0.09
    POSITIVE LOGITS
     Confirmation
    0.10
     confirm
    0.09
     Confirm
    0.09
     confirmed
    0.09
     Modi
    0.09
    bal
    0.09
     ar
    0.09
     Ab
    0.09
    gend
    0.08
     lux
    0.08
    Activations Density 0.001%

    No Known Activations