© 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. 33147
    Prev
    Next
    INDEX
    Explanations

    actions to spread

    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
     Miche
    -0.14
     wich
    -0.13
     atleast
    -0.12
     whats
    -0.12
     ,(
    -0.12
     ,↵↵
    -0.12
     frankly
    -0.11
    Lets
    -0.11
     ,↵
    -0.11
     Whats
    -0.10
    POSITIVE LOGITS
    -plus
    0.20
     oft
    0.14
    -than
    0.14
    /etc
    0.13
    /from
    0.12
     PLUS
    0.12
    -and
    0.12
    -needed
    0.12
    (es
    0.12
     needing
    0.11
    Activations Density 5.053%

    No Known Activations