© 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. 4811
    Prev
    Next
    INDEX
    Explanations

    permanently, permanently, permanent, forever, indefinitely

    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
    ulin
    -0.11
     procur
    -0.10
    jab
    -0.10
    lez
    -0.10
     puls
    -0.10
    aho
    -0.10
     Whip
    -0.10
    zano
    -0.09
    avanaugh
    -0.09
    kar
    -0.09
    POSITIVE LOGITS
     permanently
    0.55
     permanent
    0.52
     Permanent
    0.44
    Permanent
    0.41
    permanent
    0.38
     perman
    0.38
     forever
    0.37
     Forever
    0.32
     irreversible
    0.29
     indefinitely
    0.28
    Activations Density 0.470%

    No Known Activations