© 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. 26194
    Prev
    Next
    INDEX
    Explanations

    response 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
    Eventually
    -0.07
    ears
    -0.07
     curl
    -0.07
    lee
    -0.07
    Ultimately
    -0.07
     suddenly
    -0.06
     dic
    -0.06
     once
    -0.06
    yro
    -0.06
     Suddenly
    -0.06
    POSITIVE LOGITS
     replied
    0.17
    “Yes
    0.14
     reply
    0.14
     RESPONSE
    0.13
     responded
    0.13
    "Yes
    0.13
     nodded
    0.13
     Reply
    0.12
     yeah
    0.12
     Replies
    0.12
    Activations Density 0.007%

    No Known Activations