© 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. 32901
    Prev
    Next
    INDEX
    Explanations

    pronouns you me us

    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
    hti
    -0.09
    IOS
    -0.08
     дел
    -0.08
     Saying
    -0.08
    ustom
    -0.08
    -double
    -0.08
    /sl
    -0.08
    lass
    -0.07
    decay
    -0.07
    IFn
    -0.07
    POSITIVE LOGITS
     welcome
    0.11
     Homes
    0.09
    vie
    0.09
    sar
    0.09
     Pike
    0.09
    ","\
    0.09
     Krish
    0.09
    izando
    0.09
     Tops
    0.09
    prar
    0.09
    Activations Density 0.001%

    No Known Activations