© 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. 32656
    Prev
    Next
    INDEX
    Explanations

    caught in / trapped in

    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
    ays
    -0.10
     scarce
    -0.09
    iek
    -0.09
     proceeding
    -0.09
     reap
    -0.09
     Pow
    -0.09
     delegates
    -0.09
     Garrison
    -0.09
    ooks
    -0.09
    sto
    -0.09
    POSITIVE LOGITS
     trap
    0.16
     headlights
    0.13
     lie
    0.12
     Trap
    0.12
     nets
    0.12
     net
    0.12
     grip
    0.11
     traps
    0.11
     webs
    0.11
     embrace
    0.11
    Activations Density 0.034%

    No Known Activations