© 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. 27128
    Prev
    Next
    INDEX
    Explanations

    program executable

    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
    issant
    -0.09
    mith
    -0.09
     brill
    -0.08
    alg
    -0.08
    Aus
    -0.08
    nap
    -0.08
    iginal
    -0.08
     clearly
    -0.08
    lian
    -0.08
    onis
    -0.08
    POSITIVE LOGITS
     forgot
    0.10
    ç«
    0.10
    èĤ
    0.09
     somew
    0.09
     cl
    0.09
     Forgotten
    0.09
     Infinity
    0.09
     infinity
    0.09
     cheats
    0.09
     caval
    0.09
    Activations Density 0.001%

    No Known Activations