© 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. 91858
    Prev
    Next
    INDEX
    Explanations

    resistant

    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
     -↵↵
    -0.19
    -↵↵
    -0.19
    -↵
    -0.17
    -
    -0.17
     -
    -0.17
     -↵
    -0.16
     ...
    -0.14
    -"
    -0.14
     ’
    -0.13
    -</
    -0.13
    POSITIVE LOGITS
    ??
    0.24
    ??↵↵
    0.19
     ??
    0.19
    ????
    0.17
    –
    0.17
    –and
    0.16
    ???
    0.16
    ???↵↵
    0.15
     (?)
    0.15
    âĢIJ
    0.14
    Activations Density 0.221%

    No Known Activations