© 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. 30315
    Prev
    Next
    INDEX
    Explanations

    pest eradication

    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
     Wheels
    -0.11
    (IC
    -0.11
     slick
    -0.10
     whe
    -0.10
     Signature
    -0.10
    ansk
    -0.09
    elin
    -0.09
     theft
    -0.09
     reversible
    -0.09
     Access
    -0.09
    POSITIVE LOGITS
     exter
    0.26
     insect
    0.21
     pests
    0.20
     erad
    0.20
     Pest
    0.20
     pest
    0.20
    exter
    0.19
     eradicate
    0.18
    pest
    0.18
     creatures
    0.17
    Activations Density 0.498%

    No Known Activations