© 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. 49411
    Prev
    Next
    INDEX
    Explanations

    adjusting related words

    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
    kap
    -0.10
    onga
    -0.09
    port
    -0.09
     Tob
    -0.09
    erras
    -0.09
     prohib
    -0.09
    iali
    -0.09
     Rap
    -0.09
     update
    -0.08
     vulner
    -0.08
    POSITIVE LOGITS
     accordingly
    0.18
     adjusts
    0.14
     Adjustment
    0.14
     knobs
    0.13
    Adjust
    0.13
     Accordingly
    0.13
     downward
    0.13
     Adjust
    0.13
     adjust
    0.13
     adjustment
    0.12
    Activations Density 0.073%

    No Known Activations