© 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. 49070
    Prev
    Next
    INDEX
    Explanations

    you or our

    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
     forcibly
    -0.16
     vara
    -0.14
     obed
    -0.13
     ocas
    -0.13
    ););↵
    -0.13
    моÑĤ
    -0.13
     sixty
    -0.12
     '../../../../../
    -0.12
    >manual
    -0.12
     inde
    -0.12
    POSITIVE LOGITS
     your
    0.13
    your
    0.12
     yourself
    0.11
     upfront
    0.11
     you
    0.10
     our
    0.09
    821
    0.09
     ourselves
    0.08
     finding
    0.08
    you
    0.08
    Activations Density 0.005%

    No Known Activations