© 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. 15042
    Prev
    Next
    INDEX
    Explanations

    pretending to extort or ambush

    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
     revel
    -0.10
    è¯ķ
    -0.09
     explore
    -0.09
     reve
    -0.09
     delight
    -0.09
     pledged
    -0.09
     inspect
    -0.09
     envy
    -0.08
    tries
    -0.08
    _attempt
    -0.08
    POSITIVE LOGITS
     Pret
    0.13
     secretly
    0.13
     invited
    0.13
     ambush
    0.13
     somew
    0.13
    anno
    0.12
     pretending
    0.12
    ito
    0.12
     conco
    0.12
    invite
    0.11
    Activations Density 0.070%

    No Known Activations