© 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. 91631
    Prev
    Next
    INDEX
    Explanations

    over / above + [noun phrase]

    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
     Hers
    -0.10
    lich
    -0.09
    IGH
    -0.09
    arel
    -0.08
    _ct
    -0.08
    terior
    -0.08
    oba
    -0.08
    nth
    -0.08
     Baum
    -0.08
    ault
    -0.08
    POSITIVE LOGITS
     heads
    0.39
     Heads
    0.29
     shoulders
    0.29
    heads
    0.29
     head
    0.29
    -head
    0.27
     ears
    0.26
    head
    0.24
     Head
    0.22
    (head
    0.22
    Activations Density 0.093%

    No Known Activations