© 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. 32499
    Prev
    Next
    INDEX
    Explanations

    places and events

    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
    YG
    -0.06
    iplinary
    -0.06
    <|endoftext|>
    -0.06
     "...
    -0.06
     hol
    -0.05
    -0.05
    heets
    -0.05
     intox
    -0.05
    uez
    -0.05
     Kale
    -0.05
    POSITIVE LOGITS
    Ľå»º
    0.13
     \""
    0.12
    ķìĿ¸
    0.11
    _MEM
    0.11
    :\/\/
    0.10
     nuova
    0.10
     senza
    0.10
     xlim
    0.10
    lineno
    0.10
     naj
    0.10
    Activations Density 5.863%

    No Known Activations