© 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. 18316
    Prev
    Next
    INDEX
    Explanations

    results tagged ‘

    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
    ents
    -0.09
     Vie
    -0.09
     Boeh
    -0.09
     Kidd
    -0.09
    oram
    -0.09
     coh
    -0.08
     Bliss
    -0.08
    mens
    -0.08
    ombre
    -0.08
     Locker
    -0.08
    POSITIVE LOGITS
     Wer
    0.09
    ж
    0.09
    jd
    0.09
     ne
    0.09
    -dr
    0.09
    shot
    0.09
    desk
    0.09
     Toe
    0.09
    ervo
    0.09
    -fl
    0.09
    Activations Density 0.022%

    No Known Activations