© 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. 47456
    Prev
    Next
    INDEX
    Explanations

    inherent qualities and character traits

    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
     ceremon
    -0.12
    ynn
    -0.12
     ritual
    -0.12
    elden
    -0.11
     flagship
    -0.11
     ceremonial
    -0.10
    elong
    -0.10
     vow
    -0.09
    ayar
    -0.09
    /pay
    -0.09
    POSITIVE LOGITS
     personality
    0.23
     Personality
    0.22
     personalities
    0.20
     intellect
    0.16
     intellectual
    0.15
     intelligence
    0.15
     equally
    0.14
     temperament
    0.13
     Intellectual
    0.13
     kindness
    0.13
    Activations Density 0.026%

    No Known Activations