© 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. 4798
    Prev
    Next
    INDEX
    Explanations

    Have you, have a, have one

    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
    rog
    -0.09
     Bhar
    -0.09
    nty
    -0.09
    ward
    -0.09
     AP
    -0.08
    atte
    -0.08
    no
    -0.08
     Elk
    -0.08
    IFn
    -0.08
    ured
    -0.08
    POSITIVE LOGITS
     mercy
    0.14
     fun
    0.13
     Fun
    0.13
     Mercy
    0.11
    illance
    0.11
     FUN
    0.11
    zens
    0.10
    ctype
    0.10
    assing
    0.10
    -not
    0.10
    Activations Density 0.063%

    No Known Activations