© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16761
    Prev
    Next
    INDEX
    Explanations

    weaknesses and vulnerabilities

    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
    ORA
    -0.12
    ora
    -0.10
    rees
    -0.10
     Fond
    -0.09
     DIN
    -0.09
    cosa
    -0.09
    outh
    -0.09
     monopol
    -0.09
     genes
    -0.08
     criminal
    -0.08
    POSITIVE LOGITS
     garlic
    0.22
     sunlight
    0.21
     Garlic
    0.18
     daylight
    0.18
     holy
    0.18
     weaknesses
    0.18
     weakness
    0.18
     silver
    0.18
     burns
    0.16
     burn
    0.16
    Activations Density 0.235%

    No Known Activations