© 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. 4829
    Prev
    Next
    INDEX
    Explanations

    license and rating information

    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
    DH
    -0.09
     Dere
    -0.09
    293
    -0.08
     crown
    -0.08
     Crown
    -0.08
     HomePage
    -0.08
    itude
    -0.08
    ita
    -0.08
    ifest
    -0.08
    ypes
    -0.08
    POSITIVE LOGITS
     Mature
    0.11
     PG
    0.10
     mature
    0.10
     Pg
    0.09
     Puppy
    0.09
     Guinness
    0.09
    PG
    0.09
     tentative
    0.09
     scho
    0.09
    itorio
    0.09
    Activations Density 0.032%

    No Known Activations