© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115419
    Prev
    Next
    INDEX
    Explanations

    mirror and reflection

    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
    cot
    -0.10
    ersen
    -0.10
     recl
    -0.10
     Auch
    -0.10
     envelop
    -0.10
    SCO
    -0.09
     volatile
    -0.09
    /pdf
    -0.09
     precaution
    -0.09
     Zum
    -0.09
    POSITIVE LOGITS
     reflection
    0.19
     reflected
    0.18
     mirror
    0.16
     Reflection
    0.16
     vanity
    0.15
     self
    0.14
    Mirror
    0.14
     Self
    0.14
     reflect
    0.14
     reflections
    0.14
    Activations Density 0.030%

    No Known Activations