© 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. 91915
    Prev
    Next
    INDEX
    Explanations

    truth be told

    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
    tings
    -0.09
     Cal
    -0.08
     nostalg
    -0.08
     cal
    -0.08
    kus
    -0.08
    tern
    -0.08
    ivity
    -0.08
     Fen
    -0.08
     Gunn
    -0.07
    aved
    -0.07
    POSITIVE LOGITS
    fully
    0.25
    ful
    0.18
    fulness
    0.17
    truth
    0.14
     truth
    0.13
    worthy
    0.13
     truthful
    0.13
    FUL
    0.13
    FULL
    0.13
    iness
    0.13
    Activations Density 0.013%

    No Known Activations