© 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. 6078
    Prev
    Next
    INDEX
    Explanations

    pragma once

    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
    [d
    -0.10
    ause
    -0.10
    mute
    -0.10
    otos
    -0.09
    arte
    -0.09
    alah
    -0.09
     Sho
    -0.09
    ocks
    -0.09
    -san
    -0.09
    ari
    -0.09
    POSITIVE LOGITS
    âĢij
    0.07
     Vic
    0.07
     quot
    0.07
     suite
    0.07
    ï¸ı
    0.07
     tang
    0.07
     McN
    0.07
    Ñİ
    0.06
     interrogation
    0.06
     dresser
    0.06
    Activations Density 1.890%

    No Known Activations