© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5326
    Prev
    Next
    INDEX
    Explanations

    Go toward

    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
     indefinitely
    -0.08
    pons
    -0.08
    819
    -0.08
     whenever
    -0.08
    Ken
    -0.08
     nostr
    -0.07
     pew
    -0.07
    NI
    -0.07
     tam
    -0.07
    get
    -0.07
    POSITIVE LOGITS
     vind
    0.11
     brid
    0.10
     Mata
    0.10
    brid
    0.10
    EDIA
    0.10
     Minor
    0.10
     Berger
    0.10
     scalar
    0.10
     Dynam
    0.10
    _sid
    0.10
    Activations Density 0.063%

    No Known Activations