© 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. 115539
    Prev
    Next
    INDEX
    Explanations

    head drops, drop attacks

    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
     patiently
    -0.12
    Waiting
    -0.11
     bored
    -0.10
     simmer
    -0.10
     gently
    -0.10
     quietly
    -0.09
     Waiting
    -0.09
     slowly
    -0.09
     boredom
    -0.09
     gentle
    -0.09
    POSITIVE LOGITS
     screaming
    0.14
     uncont
    0.14
     conv
    0.13
     erratic
    0.13
     frantic
    0.13
     shri
    0.12
     scream
    0.12
     yelling
    0.12
     screams
    0.12
     screamed
    0.12
    Activations Density 0.020%

    No Known Activations