© 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. 33356
    Prev
    Next
    INDEX
    Explanations

    PostgreSQL posts

    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
    posts
    -0.10
    ла
    -0.09
    ìł
    -0.09
    fram
    -0.09
    /inc
    -0.09
     Trou
    -0.09
    kel
    -0.08
    bcc
    -0.08
     posted
    -0.08
    raf
    -0.08
    POSITIVE LOGITS
    erior
    0.22
    graduate
    0.21
    ulate
    0.19
    greSQL
    0.19
    ulated
    0.18
    modern
    0.17
    ulates
    0.17
    hum
    0.17
     facto
    0.17
     hoc
    0.16
    Activations Density 0.149%

    No Known Activations