© 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. 48496
    Prev
    Next
    INDEX
    Explanations

    a followed by noun

    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
     lot
    -0.15
    pace
    -0.14
    woke
    -0.13
    ointed
    -0.13
    holds
    -0.13
    .lot
    -0.13
    izen
    -0.13
    abouts
    -0.12
    sembly
    -0.12
    esthes
    -0.12
    POSITIVE LOGITS
     bele
    0.07
     ÂŃ
    0.07
    âĢ¦I
    0.07
    otos
    0.07
    LOB
    0.06
    nth
    0.06
     Bols
    0.06
    itti
    0.06
     purely
    0.06
     Nach
    0.06
    Activations Density 1.502%

    No Known Activations