© 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. 27000
    Prev
    Next
    INDEX
    Explanations

    flag

    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
     Contacts
    -0.09
    ariat
    -0.09
    orgen
    -0.09
     contacts
    -0.08
     gro
    -0.08
    obil
    -0.08
    /lic
    -0.08
     Chill
    -0.08
     cord
    -0.08
     apost
    -0.08
    POSITIVE LOGITS
     flag
    0.27
     Flag
    0.26
    Flag
    0.24
     flags
    0.24
     Flags
    0.22
    flag
    0.21
     FLAG
    0.21
    -flag
    0.20
    FLAG
    0.20
    (flag
    0.18
    Activations Density 0.209%

    No Known Activations