© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111731
    Prev
    Next
    INDEX
    Explanations

    interrupt or interfere

    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
     rigged
    -0.10
    cz
    -0.10
     suffer
    -0.10
     inaccessible
    -0.10
     exaggerated
    -0.10
    uffers
    -0.09
     Rac
    -0.09
     suffers
    -0.09
     tortured
    -0.09
     hypnot
    -0.09
    POSITIVE LOGITS
     interrupt
    0.39
     disrupting
    0.35
     disrupt
    0.35
     interruption
    0.34
     interrupts
    0.34
     interruptions
    0.33
     Interrupt
    0.30
     ruining
    0.30
     interfere
    0.30
     interfering
    0.30
    Activations Density 0.555%

    No Known Activations