© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115379
    Prev
    Next
    INDEX
    Explanations

    determine sincerity authenticity

    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
     ca
    -0.09
     tend
    -0.07
    kur
    -0.07
    ogn
    -0.07
     {'
    -0.07
    umba
    -0.07
     Boom
    -0.07
    :
    -0.07
     several
    -0.07
     retreat
    -0.07
    POSITIVE LOGITS
     sincerity
    0.14
     genuine
    0.13
     authenticity
    0.13
     youre
    0.13
     legitimacy
    0.12
     genu
    0.12
     Genuine
    0.12
     ethnicity
    0.11
    /Dk
    0.11
    aines
    0.11
    Activations Density 0.007%

    No Known Activations