© 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. 116806
    Prev
    Next
    INDEX
    Explanations

    escape from or getaway from

    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
    ele
    -0.11
    usi
    -0.10
    azon
    -0.10
    mando
    -0.10
     Dil
    -0.10
     Patron
    -0.10
     bait
    -0.10
    izzo
    -0.10
    jm
    -0.10
    #"
    -0.10
    POSITIVE LOGITS
     escape
    0.22
     escaping
    0.18
     Escape
    0.18
     escapes
    0.16
     escap
    0.16
    escape
    0.15
     Esc
    0.15
    Escape
    0.14
     escaped
    0.14
     reality
    0.14
    Activations Density 0.022%

    No Known Activations