© 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. 47966
    Prev
    Next
    INDEX
    Explanations

    forever chasing discontent

    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
     Shank
    -0.08
     aust
    -0.08
    nk
    -0.08
     austerity
    -0.08
     unk
    -0.07
    jk
    -0.07
    arah
    -0.07
    hide
    -0.07
    lc
    -0.07
    uffy
    -0.07
    POSITIVE LOGITS
     continually
    0.19
     constantly
    0.18
     endlessly
    0.17
     discontent
    0.16
     continuously
    0.16
     restless
    0.15
     indefinitely
    0.15
     chasing
    0.15
     forever
    0.15
     chase
    0.15
    Activations Density 0.014%

    No Known Activations