© 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. 29181
    Prev
    Next
    INDEX
    Explanations

    code headers and data structures

    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
    loe
    -0.11
    apore
    -0.09
    Attr
    -0.09
    tober
    -0.09
     Campo
    -0.09
    [](
    -0.08
    ätz
    -0.08
    lops
    -0.08
     WALL
    -0.08
     glo
    -0.08
    POSITIVE LOGITS
     "
    0.16
     “âĢ¦
    0.13
     “
    0.13
     "...
    0.13
    ï¼Į“
    0.10
    ("
    0.10
     "..
    0.10
     "_
    0.10
    "Now
    0.09
     "*
    0.09
    Activations Density 0.022%

    No Known Activations