© 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. 6430
    Prev
    Next
    INDEX
    Explanations

    overall goals and outcomes

    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
     overall
    -0.22
     Overall
    -0.19
    overall
    -0.17
    Overall
    -0.16
     overarching
    -0.13
     total
    -0.11
     generally
    -0.10
     general
    -0.10
    æĢ»
    -0.10
     Generally
    -0.09
    POSITIVE LOGITS
     impression
    0.13
     Schul
    0.11
     Jah
    0.11
    ExceptionHandler
    0.11
    viz
    0.11
     Yates
    0.11
     Sullivan
    0.10
    bum
    0.10
    ìłģ
    0.10
     picture
    0.10
    Activations Density 0.102%

    No Known Activations