© 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. 116682
    Prev
    Next
    INDEX
    Explanations

    overcoming obstacles or restrictions

    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
     ark
    -0.10
    chu
    -0.10
    ivr
    -0.09
    ograd
    -0.09
     invol
    -0.09
    Enumerable
    -0.09
    lint
    -0.09
     pardon
    -0.09
    lug
    -0.09
     Chun
    -0.09
    POSITIVE LOGITS
     obstacles
    0.21
     obstacle
    0.18
     restrictions
    0.17
     circum
    0.16
     defenses
    0.16
     barriers
    0.14
     bypass
    0.14
     limitations
    0.14
     evade
    0.13
     safeguards
    0.13
    Activations Density 0.083%

    No Known Activations