© 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. 112807
    Prev
    Next
    INDEX
    Explanations

    years ago, birthdays, earlier

    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
     forgot
    -0.13
    Ware
    -0.12
    usch
    -0.10
     got
    -0.09
     withdrew
    -0.09
    forgot
    -0.09
    ware
    -0.09
    æŃ£åľ¨
    -0.09
     grew
    -0.09
    inem
    -0.09
    POSITIVE LOGITS
     hadn
    0.26
     had
    0.22
    had
    0.17
     hade
    0.16
    ’ve
    0.16
     telah
    0.15
     avait
    0.15
     been
    0.14
    've
    0.14
     Ive
    0.14
    Activations Density 0.235%

    No Known Activations