© 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. 47481
    Prev
    Next
    INDEX
    Explanations

    siege and fortifications

    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
     hunting
    -0.13
     Hunting
    -0.13
     hunts
    -0.12
     hunted
    -0.12
     hunt
    -0.11
     Cycl
    -0.10
     hunter
    -0.10
     leases
    -0.10
    APE
    -0.10
     Cabinet
    -0.10
    POSITIVE LOGITS
     defenders
    0.27
     siege
    0.26
     besie
    0.22
     defenses
    0.22
     defense
    0.22
     defensive
    0.22
     fort
    0.22
     defended
    0.22
     gates
    0.22
     defending
    0.21
    Activations Density 0.257%

    No Known Activations