© 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. 5259
    Prev
    Next
    INDEX
    Explanations

    in order to

    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
    .âĢ¢
    -0.13
    )const
    -0.12
     )"
    -0.12
     {}.
    -0.11
    )|(
    -0.11
     ++)
    -0.11
     <",
    -0.11
    but
    -0.11
     ".↵
    -0.11
     :↵↵↵↵
    -0.11
    POSITIVE LOGITS
     it
    0.25
     there
    0.25
     they
    0.25
     we
    0.24
    ,it
    0.23
     you
    0.17
    ,this
    0.17
    ,
    0.15
    there
    0.15
     theres
    0.15
    Activations Density 1.742%

    No Known Activations