© 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. 89492
    Prev
    Next
    INDEX
    Explanations

    I personally

    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
    ante
    -0.10
     Poster
    -0.10
    need
    -0.09
    417
    -0.09
     poster
    -0.09
    mis
    -0.09
     SER
    -0.08
    oi
    -0.08
     misd
    -0.08
    entes
    -0.08
    POSITIVE LOGITS
     personally
    0.30
     Personally
    0.24
    Personally
    0.22
     myself
    0.20
     recommend
    0.17
     recommending
    0.15
     personal
    0.15
     Recommend
    0.15
     Recomm
    0.13
    personal
    0.13
    Activations Density 0.153%

    No Known Activations