© 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. 111903
    Prev
    Next
    INDEX
    Explanations

    false sense of comfort

    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
     Noah
    -0.18
    iker
    -0.13
     ark
    -0.12
     Ark
    -0.11
    -No
    -0.11
    ORK
    -0.11
    greg
    -0.10
    etten
    -0.10
    ngo
    -0.10
     bounding
    -0.10
    POSITIVE LOGITS
     false
    0.17
     lul
    0.16
     falsely
    0.15
     FALSE
    0.14
     False
    0.13
    false
    0.13
    FALSE
    0.12
     illusion
    0.12
    False
    0.10
     security
    0.10
    Activations Density 0.002%

    No Known Activations