© 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. 49372
    Prev
    Next
    INDEX
    Explanations

    return or respond

    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
     backward
    -0.14
     backwards
    -0.12
     chalk
    -0.12
     behind
    -0.10
     recreate
    -0.10
    /sw
    -0.10
     Carn
    -0.10
     Coch
    -0.09
    /k
    -0.09
     recre
    -0.09
    POSITIVE LOGITS
     equally
    0.14
    /respond
    0.10
     replies
    0.10
     ident
    0.10
    /response
    0.09
     intim
    0.09
     encouragement
    0.09
    -reply
    0.09
     responds
    0.09
    obl
    0.09
    Activations Density 0.010%

    No Known Activations