© 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. 7059
    Prev
    Next
    INDEX
    Explanations

    stop words

    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
    lek
    -0.12
     forgetting
    -0.11
    zes
    -0.10
    uxe
    -0.10
     append
    -0.10
    .pa
    -0.10
     instantly
    -0.10
     thankfully
    -0.10
    efore
    -0.10
     gladly
    -0.10
    POSITIVE LOGITS
     stop
    0.14
     harder
    0.13
     Stop
    0.12
    Stop
    0.12
     STOP
    0.12
    STOP
    0.11
    _STOP
    0.11
    —are
    0.11
     tighter
    0.11
    -stop
    0.11
    Activations Density 0.005%

    No Known Activations