© 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. 16435
    Prev
    Next
    INDEX
    Explanations

    referring to or targeting

    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
     Incorpor
    -0.10
    åĪ©
    -0.10
    andel
    -0.10
    put
    -0.09
     Authors
    -0.09
     bund
    -0.09
    Contrib
    -0.09
    ucha
    -0.09
    642
    -0.09
     incorporating
    -0.09
    POSITIVE LOGITS
     target
    0.20
     referring
    0.19
     directed
    0.17
     targeting
    0.17
     targets
    0.17
     refers
    0.17
     targeted
    0.16
     Target
    0.15
     refer
    0.15
     Targets
    0.15
    Activations Density 0.477%

    No Known Activations