© 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. 25772
    Prev
    Next
    INDEX
    Explanations

    east asian script characters

    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
    csi
    -0.08
     imminent
    -0.08
     Creat
    -0.08
    <|fim_suffix|>
    -0.07
     conc
    -0.07
    anske
    -0.07
     Cah
    -0.07
     eminent
    -0.07
    ffield
    -0.06
     stew
    -0.06
    POSITIVE LOGITS
    âĢİ
    0.14
    /en
    0.12
    ï¸ı
    0.12
    µ¬
    0.12
    LAY
    0.12
     comercial
    0.11
     zw
    0.10
    Ĺı
    0.10
    àµįà´
    0.10
    łĢ
    0.10
    Activations Density 0.062%

    No Known Activations