© 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. 50533
    Prev
    Next
    INDEX
    Explanations

    mail message or domain

    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
    amel
    -0.08
    alamat
    -0.08
    (Of
    -0.08
     SqlCommand
    -0.07
     BaÅŁ
    -0.07
     fir
    -0.07
    agged
    -0.07
    ött
    -0.07
    gies
    -0.07
    ç±
    -0.07
    POSITIVE LOGITS
     dotenv
    0.09
    earn
    0.08
    DSL
    0.08
     viv
    0.08
    dma
    0.08
    uspend
    0.08
    (inner
    0.08
    orian
    0.08
    Ñħод
    0.08
     gloss
    0.08
    Activations Density 0.037%

    No Known Activations