© 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. 30450
    Prev
    Next
    INDEX
    Explanations

    code comments and headers

    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
    ights
    -0.13
     Schro
    -0.10
     fingertips
    -0.09
    лÑİ
    -0.09
    âĢ»
    -0.09
    Scoped
    -0.09
    tl
    -0.08
    quis
    -0.08
     Democr
    -0.08
    iel
    -0.08
    POSITIVE LOGITS
     WTF
    0.13
     replied
    0.11
     OMG
    0.11
     OK
    0.11
     Replies
    0.10
    reply
    0.10
     well
    0.10
     WOW
    0.10
    plat
    0.10
    RESP
    0.10
    Activations Density 0.011%

    No Known Activations