© 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. 116174
    Prev
    Next
    INDEX
    Explanations

    virtual directory, expire globally

    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
    loh
    -0.07
     teh
    -0.06
     thank
    -0.06
     pratic
    -0.06
    enet
    -0.06
     cater
    -0.06
    enal
    -0.06
    elsen
    -0.06
    ichten
    -0.06
    Composer
    -0.06
    POSITIVE LOGITS
    ÐĤ
    0.19
    riad
    0.13
    soever
    0.12
    quete
    0.12
    ÑģÑı
    0.11
    uary
    0.11
    SION
    0.11
     optimized
    0.11
    egot
    0.11
    éĹ´
    0.11
    Activations Density 0.012%

    No Known Activations