© 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. 29358
    Prev
    Next
    INDEX
    Explanations

    read more

    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
     Ying
    -0.10
    hg
    -0.09
    Vars
    -0.09
    endar
    -0.09
    419
    -0.09
    HG
    -0.09
    JK
    -0.08
    ifix
    -0.08
    jac
    -0.08
     Carousel
    -0.08
    POSITIVE LOGITS
     Blick
    0.10
     comm
    0.10
     rout
    0.09
     footsteps
    0.09
     Dram
    0.09
     patched
    0.09
    iego
    0.08
    _more
    0.08
     sembl
    0.08
     Phar
    0.08
    Activations Density 0.012%

    No Known Activations