© 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. 50031
    Prev
    Next
    INDEX
    Explanations

    citations and encoded identifiers

    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
    lest
    -0.13
    	↵	↵	↵
    -0.09
    ges
    -0.08
    bourne
    -0.08
     subdir
    -0.07
    ÑĤа
    -0.07
    ed
    -0.07
    iest
    -0.07
    ories
    -0.07
    vell
    -0.07
    POSITIVE LOGITS
     Downing
    0.21
    acious
    0.18
    acity
    0.15
    isman
    0.14
    th
    0.13
    porno
    0.13
    nis
    0.12
     Clover
    0.12
    ents
    0.12
    anted
    0.12
    Activations Density 0.248%

    No Known Activations