© 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. 49826
    Prev
    Next
    INDEX
    Explanations

    kidnappedhostagesspiesoperativesassassins

    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
     dro
    -0.11
     insan
    -0.10
     enamel
    -0.10
     releg
    -0.10
     endian
    -0.10
     emulation
    -0.10
     Couch
    -0.10
     emanc
    -0.10
     recl
    -0.10
     pads
    -0.10
    POSITIVE LOGITS
     assass
    0.16
     hostage
    0.16
     spies
    0.15
     reinforcements
    0.14
     arrests
    0.14
     operatives
    0.14
     hostages
    0.14
     ambush
    0.13
     kidnapped
    0.13
     surveillance
    0.13
    Activations Density 0.040%

    No Known Activations