© 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. 115986
    Prev
    Next
    INDEX
    Explanations

    people obtaining or living

    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
    /people
    -0.13
     people
    -0.10
    people
    -0.10
     barr
    -0.09
     Hosp
    -0.09
     Dou
    -0.08
     alike
    -0.08
     Barr
    -0.08
     peoples
    -0.07
     Bew
    -0.07
    POSITIVE LOGITS
     Wolff
    0.11
    semb
    0.10
    tdown
    0.10
     deutschland
    0.10
    urs
    0.10
     INCIDENT
    0.10
    AGE
    0.10
    anke
    0.10
    meg
    0.10
    ALSE
    0.10
    Activations Density 0.064%

    No Known Activations