© 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. 17021
    Prev
    Next
    INDEX
    Explanations

    claiming or pretending

    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
    mods
    -0.12
    CLU
    -0.12
    ?key
    -0.11
    voy
    -0.11
    cke
    -0.11
     outlines
    -0.11
     sta
    -0.10
     Dere
    -0.10
     Respons
    -0.10
    jak
    -0.10
    POSITIVE LOGITS
     pretend
    0.39
     pretending
    0.38
     claiming
    0.37
     pretended
    0.36
     falsely
    0.31
     Pret
    0.31
     pret
    0.30
     claim
    0.30
    pret
    0.30
     Claim
    0.30
    Activations Density 0.263%

    No Known Activations