© 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. 28910
    Prev
    Next
    INDEX
    Explanations

    person as a candidate or better person

    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
     Maxim
    -0.09
    eres
    -0.08
    angan
    -0.08
    lobber
    -0.08
     gor
    -0.08
    _singular
    -0.08
     langs
    -0.08
    inka
    -0.08
     pract
    -0.08
    omnia
    -0.08
    POSITIVE LOGITS
     person
    0.26
     personality
    0.25
     character
    0.24
     personalities
    0.23
     personally
    0.21
    person
    0.21
     morally
    0.21
    Person
    0.20
     PERSON
    0.19
     Person
    0.19
    Activations Density 0.207%

    No Known Activations