© 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. 116550
    Prev
    Next
    INDEX
    Explanations

    location measurement

    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
     Schro
    -0.10
    &eacute
    -0.09
    cla
    -0.09
     ...)↵
    -0.09
     Scho
    -0.09
     Mickey
    -0.09
    "d
    -0.09
     Capitals
    -0.09
     theirs
    -0.09
    yar
    -0.09
    POSITIVE LOGITS
     ,
    0.13
     —
    0.13
     pounds
    0.11
     ;
    0.11
     ounces
    0.10
     ,[
    0.10
     ()
    0.10
     onward
    0.10
     onwards
    0.10
    —from
    0.10
    Activations Density 0.164%

    No Known Activations