© 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. 17100
    Prev
    Next
    INDEX
    Explanations

    received / was / signed / led

    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
     ust
    -0.09
    lsa
    -0.09
    ffield
    -0.09
    ième
    -0.09
     коÑĤоÑĢ
    -0.09
     refl
    -0.08
     Sof
    -0.08
     bÄĻdÄħ
    -0.08
    obe
    -0.08
    AMED
    -0.08
    POSITIVE LOGITS
     moreover
    0.35
     therefore
    0.33
     meanwhile
    0.32
     however
    0.31
     nowadays
    0.29
     furthermore
    0.29
     unfortunately
    0.28
     nevertheless
    0.26
     indeed
    0.26
     lately
    0.25
    Activations Density 1.844%

    No Known Activations