© 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. 18181
    Prev
    Next
    INDEX
    Explanations

    responds to stimuli

    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
     Overnight
    -0.09
     Bett
    -0.09
     eyeb
    -0.09
    acha
    -0.09
    WR
    -0.09
    aris
    -0.09
     nets
    -0.09
     Iterate
    -0.08
    cken
    -0.08
    detach
    -0.08
    POSITIVE LOGITS
     responsive
    0.23
     responsiveness
    0.22
     respond
    0.21
     responds
    0.20
     responding
    0.20
     reacts
    0.20
     reacting
    0.19
    -responsive
    0.19
     Responsive
    0.18
     responded
    0.18
    Activations Density 0.837%

    No Known Activations