© 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. 114234
    Prev
    Next
    INDEX
    Explanations

    look of, look'n'

    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
     viewing
    -0.09
    -looking
    -0.08
     lam
    -0.07
     Princip
    -0.07
     Seeing
    -0.07
     wrists
    -0.07
     seeing
    -0.07
     prof
    -0.07
    RED
    -0.07
    jal
    -0.06
    POSITIVE LOGITS
     desperation
    0.13
     generalized
    0.12
    AndFeel
    0.11
    ORIZ
    0.11
     (!((
    0.11
     Quart
    0.11
    IDEO
    0.11
     param
    0.11
     unanimous
    0.11
     bree
    0.10
    Activations Density 0.007%

    No Known Activations