© 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. 47942
    Prev
    Next
    INDEX
    Explanations

    get out of trouble

    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
     luck
    -0.07
    ury
    -0.07
     willing
    -0.07
    mall
    -0.07
     bip
    -0.07
     Unlimited
    -0.07
     Clarkson
    -0.07
     access
    -0.07
     interesting
    -0.07
     reluctant
    -0.07
    POSITIVE LOGITS
     hurt
    0.13
     tangled
    0.12
     ens
    0.12
     chopped
    0.11
     Arrest
    0.11
     Shaft
    0.11
     kicked
    0.11
     str
    0.11
     seper
    0.11
     themselves
    0.10
    Activations Density 0.058%

    No Known Activations