© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87992
    Prev
    Next
    INDEX
    Explanations

    looking for

    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
    arta
    -0.09
    ika
    -0.09
    icus
    -0.09
     habit
    -0.09
     CB
    -0.09
    yme
    -0.08
    aises
    -0.08
     Nin
    -0.08
     PR
    -0.08
    OV
    -0.08
    POSITIVE LOGITS
     seeking
    0.19
     looking
    0.17
     searching
    0.17
     seek
    0.16
     Seeking
    0.15
    Searching
    0.15
     search
    0.14
     seeks
    0.14
    looking
    0.13
     Searching
    0.13
    Activations Density 0.025%

    No Known Activations