© 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. 15428
    Prev
    Next
    INDEX
    Explanations

    caution about strangers

    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
    mand
    -0.12
     Garner
    -0.10
     coherent
    -0.10
     fortunate
    -0.10
     vic
    -0.09
    requ
    -0.09
    ivor
    -0.09
    Preferred
    -0.09
     vom
    -0.09
     respected
    -0.09
    POSITIVE LOGITS
     trusting
    0.30
     blindly
    0.28
     trust
    0.21
     trusts
    0.21
     Trust
    0.20
     strangers
    0.20
     stranger
    0.20
     unfamiliar
    0.19
     entr
    0.18
     unknown
    0.18
    Activations Density 0.088%

    No Known Activations