© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115580
    Prev
    Next
    INDEX
    Explanations

    FOR/exception/accordance/license

    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
     repe
    -0.11
    cae
    -0.10
    Topic
    -0.09
    etail
    -0.09
    seg
    -0.09
     jt
    -0.09
     tails
    -0.09
    opers
    -0.09
    CAST
    -0.09
    )--
    -0.09
    POSITIVE LOGITS
     refl
    0.09
     Shepard
    0.08
     intuit
    0.08
    angs
    0.08
     Mint
    0.08
     uncompressed
    0.08
    /open
    0.08
     Meh
    0.08
     (*.
    0.07
     redistrib
    0.07
    Activations Density 0.008%

    No Known Activations