© 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. 49148
    Prev
    Next
    INDEX
    Explanations

    years old

    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
     “[
    -0.16
    —that
    -0.14
    —I
    -0.14
     qua
    -0.14
    —"
    -0.14
    —or
    -0.13
     âĢ¦↵↵
    -0.13
     tête
    -0.12
    [^
    -0.12
    —at
    -0.12
    POSITIVE LOGITS
     seperate
    0.22
     seper
    0.21
     alot
    0.21
     isnt
    0.19
     Womens
    0.18
     thru
    0.18
     thats
    0.18
     recieved
    0.18
     theres
    0.17
     doesnt
    0.17
    Activations Density 1.699%

    No Known Activations