© 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. 115882
    Prev
    Next
    INDEX
    Explanations

    naïve or trusting actions

    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
     mocking
    -0.11
     bully
    -0.11
    isch
    -0.10
     bullying
    -0.10
     malicious
    -0.10
     teasing
    -0.10
     mast
    -0.10
     prank
    -0.10
     Orn
    -0.10
     cruelty
    -0.10
    POSITIVE LOGITS
     naive
    0.18
     succ
    0.17
     na
    0.15
     naï
    0.15
     blindly
    0.15
     susceptibility
    0.14
     trusting
    0.14
     Na
    0.13
     Entr
    0.13
     unwitting
    0.13
    Activations Density 0.082%

    No Known Activations