© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90090
    Prev
    Next
    INDEX
    Explanations

    out of control; cannot change

    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
     Cath
    -0.10
    /watch
    -0.10
     comm
    -0.10
     slu
    -0.09
    adc
    -0.09
    igator
    -0.09
     loginUser
    -0.09
    wen
    -0.09
     WATCH
    -0.09
    fee
    -0.09
    POSITIVE LOGITS
     definitive
    0.11
     facts
    0.11
    avatar
    0.10
     Modify
    0.10
    _change
    0.09
     modification
    0.09
     Modification
    0.09
     conce
    0.09
     change
    0.09
     Change
    0.09
    Activations Density 0.005%

    No Known Activations