© 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. 29131
    Prev
    Next
    INDEX
    Explanations

    Mend and Mendelian

    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
    ADER
    -0.08
     Exact
    -0.07
    adh
    -0.07
    umu
    -0.07
     Rus
    -0.07
    n
    -0.07
     topping
    -0.07
     Ballard
    -0.07
    mani
    -0.07
     synd
    -0.06
    POSITIVE LOGITS
    igure
    0.14
    ez
    0.14
     mend
    0.13
    elian
    0.13
    rzy
    0.13
     Mend
    0.13
    endez
    0.13
     fences
    0.12
    lew
    0.12
    okus
    0.12
    Activations Density 0.009%

    No Known Activations