© 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. 15559
    Prev
    Next
    INDEX
    Explanations

    into the eyes

    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
    ibi
    -0.10
     stretching
    -0.10
     Stretch
    -0.09
    weg
    -0.09
     stretch
    -0.09
    ISK
    -0.09
     leve
    -0.09
     promin
    -0.09
     Ned
    -0.09
     hull
    -0.09
    POSITIVE LOGITS
     eyes
    0.22
     Eyes
    0.20
    eyes
    0.19
     eye
    0.18
     wounds
    0.18
     wound
    0.17
    eye
    0.16
    çľ
    0.15
    -eye
    0.14
     sensitive
    0.14
    Activations Density 0.107%

    No Known Activations