© 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. 112856
    Prev
    Next
    INDEX
    Explanations

    featuring, starring, involving, depicting, showcasing

    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
    ">↵↵↵
    -0.09
     removeAll
    -0.09
    -posts
    -0.09
     descon
    -0.09
     wired
    -0.09
    /assets
    -0.08
    atta
    -0.08
     omnip
    -0.08
     indiscrim
    -0.08
     crib
    -0.08
    POSITIVE LOGITS
     featuring
    0.29
     Featuring
    0.21
     involving
    0.18
     starring
    0.17
     titled
    0.16
     features
    0.16
     depicting
    0.15
     showcasing
    0.14
    itled
    0.14
     involves
    0.14
    Activations Density 0.098%

    No Known Activations